08_dge_culture_lichen

Rationale: This script performs differential gene expression (dge) and calculates the upregulated and downregulated genes in lichen samples versus Xanthoria culture samples using edgeR and Sleuth

1. Prepare

Load the libraries

Create counts table from kallisto output which will be used for further dge analysis

counts<-read.delim2("../analysis_and_temp_files/06_meta_mapping/kallisto_mycobiont_only.txt",sep=" ")
metadata<-read.csv2("../analysis_and_temp_files/06_meta_mapping/metadata_shared_with_neha.csv",sep=",")

# Extract locus_tag from target_id (XANPAGTX0501 for nuclear genome and GTX0501mito for mito genome) - OPTIONAL
counts[c("locus_tag","rest")]<-str_split_fixed(counts$target_id,'_',n=2)

# Tabulate the counts
counts_tab<-pivot_wider(counts[c(1,4,6)],names_from=sample,values_from = est_counts)
head(counts_tab)

## # A tibble: 6 × 32
##   target_id   XBC2  XBA1  XSA2_2 XSC1  XSE2  XBE1  XTA2  XSC2  XSA2  XBA2  XBC1 
##   <chr>       <chr> <chr> <chr>  <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 XANPAGTX05… 270   535   593.5  248   335.5 288   484   324.5 429.5 408   324.5
## 2 XANPAGTX05… 194   131   284.5  112   171.5 132   257.5 144   179.5 187   81   
## 3 XANPAGTX05… 191.5 305   264.5  152.5 288   367   332   246.5 187.5 140   367  
## 4 XANPAGTX05… 126   43.5  119.5  60.5  40.5  34.5  87.5  45    73    258.5 43.5 
## 5 XANPAGTX05… 38    223   221    91    38    20    267   98    179   196   32   
## 6 XANPAGTX05… 205   431   487    176   180   86    332   271   320   356   114  
## # ℹ 20 more variables: XTA1 <chr>, XSA1 <chr>, MP_I <chr>, XTC2 <chr>,
## #   XTE2 <chr>, XBE2 <chr>, XMC2 <chr>, MP_II <chr>, S_21XB1 <chr>,
## #   KS21XB1 <chr>, S_21XB3 <chr>, S_42XB1 <chr>, S_42XB2 <chr>, S_42XB3 <chr>,
## #   KS48XB1 <chr>, KS48XB2 <chr>, KS48XB3 <chr>, KS9XB1 <chr>, KS9XB2 <chr>,
## #   KS9XB3 <chr>

write.table(counts_tab,"../analysis_and_temp_files/08_dge_culture_lichen/counts_table.tsv",quote=F,sep="\t",row.names = F) # Final table that will be used for dge calculation

Read the counts table (or Start running the script from this step)

full<-read.delim("../analysis_and_temp_files/08_dge_culture_lichen/counts_table.tsv",row.names=1)
d<-full %>% select(-MP_I,-MP_II) #remove MP_I and MP_II samples (based on previous correlation heatmaps)
colnames(d)

##  [1] "XBC2"    "XBA1"    "XSA2_2"  "XSC1"    "XSE2"    "XBE1"    "XTA2"   
##  [8] "XSC2"    "XSA2"    "XBA2"    "XBC1"    "XTA1"    "XSA1"    "XTC2"   
## [15] "XTE2"    "XBE2"    "XMC2"    "S_21XB1" "KS21XB1" "S_21XB3" "S_42XB1"
## [22] "S_42XB2" "S_42XB3" "KS48XB1" "KS48XB2" "KS48XB3" "KS9XB1"  "KS9XB2" 
## [29] "KS9XB3"

head(d,5:5)

##                         XBC2  XBA1 XSA2_2  XSC1  XSE2  XBE1  XTA2  XSC2  XSA2
## XANPAGTX0501_000001-T1 270.0 535.0  593.5 248.0 335.5 288.0 484.0 324.5 429.5
## XANPAGTX0501_000002-T1 194.0 131.0  284.5 112.0 171.5 132.0 257.5 144.0 179.5
## XANPAGTX0501_000003-T1 191.5 305.0  264.5 152.5 288.0 367.0 332.0 246.5 187.5
## XANPAGTX0501_000004-T1 126.0  43.5  119.5  60.5  40.5  34.5  87.5  45.0  73.0
## XANPAGTX0501_000005-T1  38.0 223.0  221.0  91.0  38.0  20.0 267.0  98.0 179.0
##                         XBA2  XBC1  XTA1 XSA1  XTC2  XTE2  XBE2  XMC2 S_21XB1
## XANPAGTX0501_000001-T1 408.0 324.5 467.5  262 364.5 292.5 164.5 353.0   700.0
## XANPAGTX0501_000002-T1 187.0  81.0 178.5  163 199.0 183.0  99.0 113.0    66.5
## XANPAGTX0501_000003-T1 140.0 367.0 414.5  134 366.5 319.0 164.5 364.5   151.5
## XANPAGTX0501_000004-T1 258.5  43.5  59.5   74  53.0  29.5  47.0  27.5    11.0
## XANPAGTX0501_000005-T1 196.0  32.0 390.0  196 122.0 100.0  13.0  41.0    22.0
##                        KS21XB1 S_21XB3 S_42XB1 S_42XB2 S_42XB3 KS48XB1 KS48XB2
## XANPAGTX0501_000001-T1   302.5   716.0   452.5   333.0   356.5   454.5   462.5
## XANPAGTX0501_000002-T1   121.5    48.5   126.5    67.0    73.0   221.0   176.5
## XANPAGTX0501_000003-T1   216.0   142.0   206.5   202.5   217.5   197.5   214.0
## XANPAGTX0501_000004-T1   212.0    43.5    68.5    97.5    79.5    43.5    45.5
## XANPAGTX0501_000005-T1    17.0    22.0    27.0    19.0    56.0    16.0    17.0
##                        KS48XB3 KS9XB1 KS9XB2 KS9XB3
## XANPAGTX0501_000001-T1   464.0  376.0  297.0  323.5
## XANPAGTX0501_000002-T1   236.5   98.0   90.0  106.0
## XANPAGTX0501_000003-T1   209.0  313.5  216.5  268.5
## XANPAGTX0501_000004-T1    37.5   91.5   36.0   78.5
## XANPAGTX0501_000005-T1     6.0   24.0   21.0   21.0

Remove lowly expressed genes

# create new column, "max" for the max read count in each row
d$max<-apply(d,1,max)
min(d$max)

## [1] 0

d1<-d[which(d$max>=5),] #to remove lowly expressed genes, keep rows in which max read count across whole panel is atleast 5

# drop the max column, as its not needed anymore
raw_counts<-d1 %>% select(-max)
length(rownames(d1)) # total number of genes

## [1] 11105

length(rownames(raw_counts)) # number after removal of lowly expressed genes

## [1] 11105

2. Generate DGE list with Sleuth

• followed tutorial here. Used the log2 transformation function following Dan’s analysis and Xia’s paper. Used following cutoffs:
  • qva<= 0.05 (standard)
  • In place of logFC cutoff, used the cutoff of abs(b)>1, following Xia’s paper

library(sleuth)
kal_dirs <- data.frame("sample"=metadata$run_id, "condition"=metadata$sample_type,
                       "path"=paste0("../analysis_and_temp_files/06_meta_mapping/kallisto_meta_mapping/",metadata$run_id,"_kallisto")) %>% filter(sample!="MP_II" & sample!="MP_I")

#define list of genes to be included: only mycobiont and only those that have  read count across whole panel of >=5
target_id<-rownames(d1)
so <- sleuth_prep(kal_dirs, extra_bootstrap_summary = TRUE,filter_target_id = target_id,transformation_function = function(x) log2(x + 0.1))

## Warning in check_num_cores(num_cores): It appears that you are running Sleuth from within Rstudio.
## Because of concerns with forking processes from a GUI, 'num_cores' is being set to 1.
## If you wish to take advantage of multiple cores, please consider running sleuth from the command line.

## reading in kallisto results

## dropping unused factor levels

## .............................
## normalizing est_counts
## A list of target IDs for filtering was found. Using this for filtering
## 11105 targets passed the filter
## normalizing tpm
## merging in metadata
## summarizing bootstraps
## .............................

so <- sleuth_fit(so, ~condition, 'full')

## fitting measurement error models
## shrinkage estimation
## 16 NA values were found during variance shrinkage estimation due to mean observation values outside of the range used for the LOESS fit.
## The LOESS fit will be repeated using exact computation of the fitted surface to extrapolate the missing values.
## These are the target ids with NA values: XANPAGTX0501_000408-T1, XANPAGTX0501_000967-T1, XANPAGTX0501_000968-T1, XANPAGTX0501_000969-T1, XANPAGTX0501_000980-T1, XANPAGTX0501_000995-T1, XANPAGTX0501_002621-T1, XANPAGTX0501_002938-T1, XANPAGTX0501_004237-T1, XANPAGTX0501_005100-T1, XANPAGTX0501_008798-T1, XANPAGTX0501_009179-T1, XANPAGTX0501_010285-T1, XANPAGTX0501_010514-T1, XANPAGTX0501_010642-T1, XANPAGTX0501_010694-T1
## computing variance of betas

so <- sleuth_fit(so, ~1, 'reduced')

## fitting measurement error models
## shrinkage estimation
## 16 NA values were found during variance shrinkage estimation due to mean observation values outside of the range used for the LOESS fit.
## The LOESS fit will be repeated using exact computation of the fitted surface to extrapolate the missing values.
## These are the target ids with NA values: XANPAGTX0501_000408-T1, XANPAGTX0501_000967-T1, XANPAGTX0501_000968-T1, XANPAGTX0501_000969-T1, XANPAGTX0501_000980-T1, XANPAGTX0501_000995-T1, XANPAGTX0501_002621-T1, XANPAGTX0501_002938-T1, XANPAGTX0501_004237-T1, XANPAGTX0501_005100-T1, XANPAGTX0501_008798-T1, XANPAGTX0501_009179-T1, XANPAGTX0501_010285-T1, XANPAGTX0501_010514-T1, XANPAGTX0501_010642-T1, XANPAGTX0501_010694-T1
## computing variance of betas

so <- sleuth_lrt(so, 'reduced', 'full')
so <- sleuth_wt(so, 'conditionxanthoria_culture')
plot_pca(so, color_by = 'condition', text_labels = TRUE,use_filtered=T,units="tpm")

sleuth_table <- sleuth_results(so, 'conditionxanthoria_culture')
sig <- sleuth_table %>% tibble::as_tibble() %>% 
  filter( qval <= 0.05, grepl("GTX0501",target_id) ) %>% 
  arrange(desc(b)) %>% mutate(change = if_else(b > 1, "culture", ifelse(b< -1, "lichen", "low_logFC")))

table(sig$change)

## 
##   culture    lichen low_logFC 
##       564      1185      4124

• Save image

pca<-plot_pca(so, color_by = 'condition', text_labels = F,use_filtered=T,units="tpm")
pca+theme_bw()+theme(text=element_text(size=7))

ggsave('../results/lichen_culture_pca.pdf',width = 4.5, height = 3)

• PCA: exploring the variation explained by the different PCs

plot_pc_variance(so,use_filtered=T,units="tpm")

• Get numeric values

ppv <- plot_pc_variance(so,use_filtered=T,units="tpm")
PCpc <- ppv$data$var
names(PCpc) <- paste0("PC", seq(1:length(PCpc)))
PCpc

##       PC1       PC2       PC3       PC4       PC5 
## 58.442702 23.237991  6.167265  3.743065  2.602711

2.3. Save gene lists

funannot<-read.delim2("../../02_mycobiont_genome/analysis_and_temp_files/06_annotate_lecanoro/Annotation_with_OG.txt",sep="\t")


sig2<-sig %>% left_join(funannot, by=c("target_id"="TranscriptID"))

upreg_sl=sig2 %>% filter(change=="lichen") %>% select(-c(CDS.transcript,Translation,gDNA,mRNA))
downreg_sl=sig2 %>% filter(change=="culture")%>% select(-c(CDS.transcript,Translation,gDNA,mRNA))

write.table(upreg_sl, "../analysis_and_temp_files/08_dge_culture_lichen/upreg_in_lichen_sleuth.txt", append="false", sep = "\t", quote=F, row.names = F)
write.table(downreg_sl, "../analysis_and_temp_files/08_dge_culture_lichen/upreg_in_culture_sleuth.txt", append="false", sep = "\t", quote=F, row.names = F)

tabd_df <- so$obs_norm[so$obs_norm$target_id %in% target_id,]
tabd_df <- dplyr::select(tabd_df, target_id, sample, 
            tpm)
tabd_df <- reshape2::dcast(tabd_df, target_id ~ sample, 
            value.var = "tpm") 
write.table(tabd_df, "../analysis_and_temp_files/08_dge_culture_lichen/norm_counts_sleuth.txt", append="false", sep = "\t", quote=F, row.names = F)

2.4. bootstrap of several genes

• Picked the gene with maximal b-value (log2 fold changes between conditions). Here, b-value > 0 means overrexpression in culture

plot_bootstrap(so, 
               target_id = sig$target_id[which.max(sig$b)], 
               units = "est_counts", 
               color_by = "condition")

• Picked the gene with minimal b-value, i.e. most strongly overrexpressed in lichen

plot_bootstrap(so, 
               target_id = sig$target_id[which.min(sig$b)], 
               units = "est_counts", 
               color_by = "condition")

• Picked the gene with minimal absolute b-value, i.e. with the lowest fold change difference. The b for it is sig$b[which.min(abs(sig$b))] and the q-value (p-value adjusted for multiple test correction) is sig$qval[which.min(abs(sig$b))], but you can see the difference between sample types somewhat

plot_bootstrap(so, 
               target_id = sig$target_id[which.min(abs(sig$b))], 
               units = "est_counts", 
               color_by = "condition")

2.5. GO enrichment analysis on sleuth

• Upregulated in lichen: largely consistent wiht the edgeR results

###make table with GO annotations
go_df <-funannot %>% select(TranscriptID,GO.Terms_new) %>% 
  mutate(GO.Terms_new = strsplit(GO.Terms_new, ",")) %>%
        unnest(GO.Terms_new) %>%
  mutate(GO.Terms=sub(".*? ", "", GO.Terms_new),
         short_term = substr(GO.Terms, 1,40))

go_data <- list(
    term2protein = data.frame(
                        term = go_df$GO.Terms_new,
                        gene = go_df$TranscriptID
                        ),
    term2name = data.frame(
                        term = go_df$GO.Terms_new,
                        name = go_df$short_term
                        ),
    
    universe = unique(as.character(go_df$TranscriptID))
)


### select genes upregulated in lichens and order them by fold change
geneList5 = sig$b[sig$change=="lichen"]
names(geneList5) = sig$target_id[sig$change=="lichen"]
geneList5 = sort(geneList5, decreasing = F)
geneList5 <- names(geneList5)

###enrichment analysis
enrich5<-clusterProfiler::enricher(geneList5,
    pAdjustMethod = "none",
    minGSSize = 1,
    maxGSSize = 2000,
    qvalueCutoff = 1,
    universe=go_data$universe,
    TERM2GENE=go_data$term2protein,
    TERM2NAME=go_data$term2name)

## 

## Registered S3 methods overwritten by 'treeio':
##   method              from    
##   MRCA.phylo          tidytree
##   MRCA.treedata       tidytree
##   Nnode.treedata      tidytree
##   Ntip.treedata       tidytree
##   ancestor.phylo      tidytree
##   ancestor.treedata   tidytree
##   child.phylo         tidytree
##   child.treedata      tidytree
##   full_join.phylo     tidytree
##   full_join.treedata  tidytree
##   groupClade.phylo    tidytree
##   groupClade.treedata tidytree
##   groupOTU.phylo      tidytree
##   groupOTU.treedata   tidytree
##   is.rooted.treedata  tidytree
##   nodeid.phylo        tidytree
##   nodeid.treedata     tidytree
##   nodelab.phylo       tidytree
##   nodelab.treedata    tidytree
##   offspring.phylo     tidytree
##   offspring.treedata  tidytree
##   parent.phylo        tidytree
##   parent.treedata     tidytree
##   root.treedata       tidytree
##   rootnode.phylo      tidytree
##   sibling.phylo       tidytree

## Registered S3 method overwritten by 'ggtree':
##   method      from 
##   identify.gg ggfun

enrichplot::dotplot(enrich5,showCategory=40,label_format=40)

• As a graph:

enrich5_pairwise<-enrichplot::pairwise_termsim(enrich5)
enrichplot::emapplot(enrich5_pairwise)

• Upregulated in culture

### select genes upregulated in lichens and order them by fold change
geneList6 = sig$b[sig$change=="culture"]
names(geneList6) = sig$target_id[sig$change=="culture"]
geneList6 = sort(geneList6, decreasing = T)
geneList6 <- names(geneList6)

###enrichment analysis
enrich6<-clusterProfiler::enricher(geneList6,
    pAdjustMethod = "none",
    minGSSize = 1,
    maxGSSize = 2000,
    qvalueCutoff = 1,
    universe=go_data$universe,
    TERM2GENE=go_data$term2protein,
    TERM2NAME=go_data$term2name)

enrichplot::dotplot(enrich6,showCategory=40,label_format=40)

• As a graph

enrich6_pairwise<-enrichplot::pairwise_termsim(enrich6)
enrichplot::emapplot(enrich6_pairwise)

2.6. InterPro enrichment analysis on sleuth

• Upregulated in lichen

###make table with IPS annotations
ips_df <-funannot %>% select(TranscriptID,InterPro_new) %>% 
  mutate(InterPro_new = strsplit(InterPro_new, ", I")) %>%
        unnest(InterPro_new) %>% mutate(InterPro_new=str_replace(InterPro_new,"^PR","IPR")) %>%
  mutate(short_term = substr(InterPro_new, 1,40))


ips_data <- list(
    term2protein = data.frame(
                        term = ips_df$InterPro_new,
                        gene = ips_df$TranscriptID
                        ),
    term2name = data.frame(
                        term = ips_df$InterPro_new,
                        name = ips_df$short_term
                        ),
    
    universe = unique(as.character(ips_df$TranscriptID))
)

enrich7<-clusterProfiler::enricher(geneList5,
    pAdjustMethod = "none",
    minGSSize = 1,
    maxGSSize = 2000,
    qvalueCutoff = 1,
    universe=ips_data$universe,
    TERM2GENE=ips_data$term2protein,
    TERM2NAME=ips_data$term2name)

enrichplot::dotplot(enrich7,showCategory=40,label_format=40)

* Upregulated in lichen as a graph

enrich7_pairwise<-enrichplot::pairwise_termsim(enrich7)
enrichplot::emapplot(enrich7_pairwise)

• Save the image

pdf(file="../results/lichen_upr.pdf",width=5,height=4)
enrichplot::emapplot(enrich7_pairwise,cex_label_category=0.4,cex_line=0.25,
                     shadowtext=F,cex_pie2axis=0.1,repel=T)
dev.off()

## quartz_off_screen 
##                 2

• Upregulated in culture

enrich8<-clusterProfiler::enricher(geneList6,
    pAdjustMethod = "none",
    minGSSize = 1,
    maxGSSize = 2000,
    qvalueCutoff = 1,
    universe=ips_data$universe,
    TERM2GENE=ips_data$term2protein,
    TERM2NAME=ips_data$term2name)

enrichplot::dotplot(enrich8,showCategory=40,label_format=40)

* Upregulated in culture as a graph

enrich8_pairwise<-enrichplot::pairwise_termsim(enrich8)
enrichplot::emapplot(enrich8_pairwise)

• Save the image

pdf(file="../results/culture_upr.pdf",width=5,height=4)
enrichplot::emapplot(enrich8_pairwise,cex_label_category=0.4,cex_line=0.25,
                     shadowtext=F,cex_pie2axis=0.1,repel=T)
dev.off()

## quartz_off_screen 
##                 2

2.7. These enrichment plots need to be taken with a grain of salt

• Among the upregulated in lichens genes only 28.9451477 % have GO annotations and 44.1350211 % have InterPro annotations
• Among the upregulated in culture genes only 41.1347518 % have GO annotations and 57.6241135 % have InterPro annotations
• These numbers are lower than general stats for the genome:
  • 47.8319177 % have GO annotations
  • 67.4564148 % have InterPro annotations
• Visualize these proportions

perc<-funannot %>% mutate(go_annotated=ifelse(!(is.na(GO.Terms_new)),"Annotated","Non-annotated"),
         ipr_annotated=ifelse(!(is.na(InterPro_new)),"Annotated","Non-annotated"),
         gene_set=case_when(
           TranscriptID %in% sig$target_id[sig$change=="culture"] ~ "Upregulated in culture",
          TranscriptID %in% sig$target_id[sig$change=="lichen"] ~ "Upregulated in lichen",
          T ~ "non-DGE"))

ipr_perc_dge<- perc %>% group_by(gene_set,ipr_annotated) %>% summarize(n=n()) %>% mutate(database="InterPro",annotated=ipr_annotated) %>% select(-ipr_annotated)

## `summarise()` has grouped output by 'gene_set'. You can override using the
## `.groups` argument.

go_perc_dge <- perc %>% group_by(gene_set,go_annotated) %>% summarize(n=n()) %>% mutate(database="GO",annotated=go_annotated) %>% select(-go_annotated)

## `summarise()` has grouped output by 'gene_set'. You can override using the
## `.groups` argument.

ipr_perc_all<- perc %>% group_by(ipr_annotated) %>% summarize(n=n()) %>% mutate(database="InterPro",gene_set="Whole transcriptome",annotated=ipr_annotated) %>% select(-ipr_annotated)
go_perc_all <- perc %>% group_by(go_annotated) %>% summarize(n=n()) %>% mutate(database="GO",gene_set="Whole transcriptome",annotated=go_annotated) %>% select(-go_annotated)
perc2<-rbind(ipr_perc_dge,go_perc_dge,ipr_perc_all,go_perc_all)
perc2$annotated<-factor(perc2$annotated,levels=c("Non-annotated","Annotated"))

ggplot(perc2 %>% filter(gene_set %in% c("Upregulated in culture","Upregulated in lichen")),
       aes(x=database,y=n,fill=annotated))+geom_bar(position="stack",stat="identity")+
  facet_wrap(~gene_set)

* Instead of two datatbases, visualize the number of proteins with any kind of functional annotation * NB: counted tRNA as being annotated

#make bar graph for DGE
perc<-funannot %>% mutate(annotated=ifelse(!(is.na(GO.Terms_new))|                                       !(is.na(CAZyme_new))| !(is.na(PFAM_new))|
                !(is.na(Protease_new))|!(is.na(InterPro_new))| KO!=""|Feature=="tRNA",
                "Annotated","Non-annotated"),
         gene_set=case_when(
           TranscriptID %in% sig$target_id[sig$change=="culture"] ~ "Upregulated in culture",
          TranscriptID %in% sig$target_id[sig$change=="lichen"] ~ "Upregulated in lichen",
          T ~ "non-DGE"))

perc_dge<- perc %>% group_by(gene_set,annotated) %>% summarize(n=n()) %>%
  group_by(gene_set) %>% mutate(perc=(100*n)/sum(n))

## `summarise()` has grouped output by 'gene_set'. You can override using the
## `.groups` argument.

dge_plot<-ggplot(perc_dge %>% filter(gene_set %in% c("Upregulated in culture","Upregulated in lichen")),
       aes(x=gene_set,y=n,fill=annotated))+geom_bar(position="stack",stat="identity")+
  geom_text(aes(label = paste0(round(perc,0),"%"),color=annotated), position=position_stack(vjust = 0.5),size=7)+
  xlab("")+ylab("# of transcripts")+ggtitle("Differentially expressed")+
  scale_fill_manual(values = c("Non-annotated"="#ffda73","Annotated"="#156902"))+
  scale_color_manual(values = c("Non-annotated"="#156902","Annotated"="#ffda73"))+ theme_minimal()+
  theme(legend.title=element_blank(),legend.position = c(0.2, 0.8),
  legend.background = element_rect(fill="white",
                                 linewidth=0.5, linetype="solid", 
                                  colour ="grey"),
  panel.grid.major.x = element_blank(),
  text = element_text(size=12),
  axis.text=element_text(size=8))

#donut plot for the whole genome
perc_all <- perc %>% group_by(annotated) %>% summarize(n=n()) %>% mutate(perc=(100*n)/sum(n))
perc_all$ymax <- cumsum(perc_all$perc)
# Compute the bottom of each rectangle
perc_all$ymin <- c(0, head(perc_all$ymax, n=-1))
# Compute label position
perc_all$labelPosition <- (perc_all$ymax + perc_all$ymin) / 2
# Compute a good label
perc_all$label <- paste0(round(perc_all$perc,0), "%")
# Make the plot
all_plot<-ggplot(perc_all, aes(ymax=ymax, ymin=ymin, xmax=4, xmin=3, fill=annotated)) +
  geom_rect() +
  geom_text( x=3.5, aes(y=labelPosition, label=label,color=annotated), size=8) +
  scale_fill_manual(values = c("Non-annotated"="#ffda73","Annotated"="#156902"))+
  scale_color_manual(values = c("Non-annotated"="#156902","Annotated"="#ffda73"))+
  coord_polar(theta="y") + ggtitle("Whole transcriptome (n = 11,185)")+
  xlim(c(2, 4)) +
  theme_void() +
  theme(legend.position = "none",text = element_text(size=12))

library(patchwork)
dge_plot+all_plot

• Save image

all_plot<-ggplot(perc_all, aes(ymax=ymax, ymin=ymin, xmax=4, xmin=3, fill=annotated)) +
  geom_rect() +
  geom_text( x=3.5, aes(y=labelPosition, label=label,color=annotated), size=2.75) +
  scale_fill_manual(values = c("Non-annotated"="#ffda73","Annotated"="#156902"))+
  scale_color_manual(values = c("Non-annotated"="#156902","Annotated"="#ffda73"))+
  coord_polar(theta="y") + ggtitle("Whole transcriptome (n = 11,185)")+
  xlim(c(2, 4)) +
  theme_void() +
  theme(legend.position = "none",text = element_text(size=8),plot.title = element_text(size=8))
dge_plot<-ggplot(perc_dge %>% filter(gene_set %in% c("Upregulated in culture","Upregulated in lichen")),
       aes(x=gene_set,y=n,fill=annotated))+geom_bar(position="stack",stat="identity")+
  geom_text(aes(label = paste0(round(perc,0),"%"),color=annotated), position=position_stack(vjust = 0.5),size=2.75)+
  xlab("")+ylab("# of transcripts")+ggtitle("Differentially expressed")+
  scale_fill_manual(values = c("Non-annotated"="#ffda73","Annotated"="#156902"))+
  scale_color_manual(values = c("Non-annotated"="#156902","Annotated"="#ffda73"))+ theme_minimal()+
  theme(legend.title=element_blank(),legend.position = c(0.2, 0.8),
  legend.background = element_rect(fill="white",
                                 linewidth=0.5, linetype="solid", 
                                  colour ="grey"),
  panel.grid.major.x = element_blank(),
  text = element_text(size=8),
  axis.text=element_text(size=6),plot.title = element_text(size=8))

pdf(file="../results/annotated_percent.pdf",width=4.5,height=3.5)
dge_plot+all_plot
dev.off()

## quartz_off_screen 
##                 2

3. Create lists for unique genes

Identified 13 genes expressed in all lichen samples and none of the culture samples.

• This list doesn’t include any potential effectors

lichen_unique<-counts_tab %>% filter(XBC2>0,XBA1>0,XSA2_2>0,XSC1>0,XSE2>0,XBE1>0,XTA2>0,XSC2>0,
  XSA2>0,XBA2>0,XBC1>0,XTA1>0,XSA1>0,XTC2>0,XTE2>0,XBE2>0,XMC2>0,
  S_21XB1==0,KS21XB1==0,S_21XB3==0,S_42XB1==0,S_42XB2==0,S_42XB3==0,
  KS48XB1==0,KS48XB2==0,KS48XB3==0,KS9XB1==0,KS9XB2==0,KS9XB3==0) %>%
  pivot_longer(-target_id,names_to="sample",values_to="counts") %>%
  filter(counts>0, sample !="MP_I",sample !="MP_II") %>% group_by(target_id) %>% summarise(avg_counts_lichen=mean(as.numeric(counts))) %>%  
  left_join(funannot, by=c("target_id"="TranscriptID")) %>%
  select(-c(CDS.transcript,Translation,gDNA,mRNA))
  
lichen_unique %>%
  kable(format = "html", col.names = colnames(lichen_unique)) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

target_id	avg_counts_lichen	GeneID	Feature	Contig	Start	Stop	Strand	Name	Product	Alias.Synonyms	EC_number	BUSCO	PFAM	InterPro	EggNog	COG	GO.Terms	Secreted	Membrane	Protease	CAZyme	antiSMASH	Notes	ProtID	CAZyme_new	COG_new	EggNog_new	GO.Terms_new	InterPro_new	PFAM_new	Protease_new	Secreted_new	KO
XANPAGTX0501_001612-T1	46.99245	XANPAGTX0501_001612	mRNA	Xp_GTX0501_2	2002693	2003141		NA	hypothetical protein	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	XANPAGTX0501_001612_T1_XANPAGTX0501_001612	NA	NA	NA	NA	NA	NA	NA	NA
XANPAGTX0501_002783-T1	18.68803	XANPAGTX0501_002783	mRNA	Xp_GTX0501_4	808460	808865		NA	hypothetical protein	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	XANPAGTX0501_002783_T1_XANPAGTX0501_002783	NA	NA	NA	NA	NA	NA	NA	NA
XANPAGTX0501_003199-T1	20.17647	XANPAGTX0501_003199	mRNA	Xp_GTX0501_5	87909	89177		AIM6_3	Altered inheritance of mitochondria protein 6	NA	NA	NA	NA	IPR017946 PLC-like phosphodiesterase, TIM beta/alpha-barrel domain superfamily;IPR039559 Altered inheritance of mitochondria protein 6, PI-PLC-like catalytic domain	ENOG503NZFJ	S:(S) Function unknown	GO_function: GO:0008081 - phosphoric diester hydrolase activity [Evidence IEA];GO_process: GO:0006629 - lipid metabolic process [Evidence IEA]	NA	NA	NA	NA	Cluster_2	NA	XANPAGTX0501_003199_T1_XANPAGTX0501_003199	NA	S:(S) Function unknown	ENOG503NZFJ	GO_function: GO:0008081 - phosphoric diester hydrolase activity [Evidence IEA], GO_process: GO:0006629 - lipid metabolic process [Evidence IEA]	IPR017946 PLC-like phosphodiesterase, TIM beta/alpha-barrel domain superfamily, IPR039559 Altered inheritance of mitochondria protein 6, PI-PLC-like catalytic domain	NA	NA	NA
XANPAGTX0501_006970-T1	48.17647	XANPAGTX0501_006970	mRNA	Xp_GTX0501_11	354394	354648		NA	hypothetical protein	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	XANPAGTX0501_006970_T1_XANPAGTX0501_006970	NA	NA	NA	NA	NA	NA	NA	NA
XANPAGTX0501_006972-T1	74.64706	XANPAGTX0501_006972	mRNA	Xp_GTX0501_11	357523	357828		NA	hypothetical protein	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	XANPAGTX0501_006972_T1_XANPAGTX0501_006972	NA	NA	NA	NA	NA	NA	NA	NA
XANPAGTX0501_008008-T1	58.88235	XANPAGTX0501_008008	mRNA	Xp_GTX0501_14	138465	139439		NA	hypothetical protein	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	XANPAGTX0501_008008_T1_XANPAGTX0501_008008	NA	NA	NA	NA	NA	NA	NA	NA
XANPAGTX0501_008856-T1	94.82353	XANPAGTX0501_008856	mRNA	Xp_GTX0501_17	399345	400886		NA	hypothetical protein	NA	NA	NA	NA	IPR032675 Leucine-rich repeat domain superfamily	NA	NA	NA	NA	NA	NA	NA	Cluster_1	NA	XANPAGTX0501_008856_T1_XANPAGTX0501_008856	NA	NA	ENOG503P83U	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR001810 F-box domain, IPR032675 Leucine-rich repeat domain superfamily	NA	NA	NA
XANPAGTX0501_009040-T1	57.41176	XANPAGTX0501_009040	mRNA	Xp_GTX0501_18	366441	366695		NA	hypothetical protein	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	XANPAGTX0501_009040_T1_XANPAGTX0501_009040	NA	NA	NA	NA	NA	NA	NA	NA
XANPAGTX0501_009438-T1	963.88235	XANPAGTX0501_009438	mRNA	Xp_GTX0501_21	196714	197521		NA	hypothetical protein	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	XANPAGTX0501_009438_T1_XANPAGTX0501_009438	NA	NA	NA	NA	NA	NA	NA	NA
XANPAGTX0501_009555-T1	1952.88235	XANPAGTX0501_009555	mRNA	Xp_GTX0501_22	191143	191546		NA	hypothetical protein	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	XANPAGTX0501_009555_T1_XANPAGTX0501_009555	NA	NA	NA	NA	NA	NA	NA	NA
XANPAGTX0501_009582-T1	17.00000	XANPAGTX0501_009582	mRNA	Xp_GTX0501_22	265438	265938		NA	hypothetical protein	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	XANPAGTX0501_009582_T1_XANPAGTX0501_009582	NA	NA	NA	NA	NA	NA	NA	NA
XANPAGTX0501_009957-T1	69.00000	XANPAGTX0501_009957	mRNA	Xp_GTX0501_27	408	679		NA	hypothetical protein	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	Cluster_1	NA	XANPAGTX0501_009957_T1_XANPAGTX0501_009957	NA	NA	NA	NA	NA	NA	NA	NA
XANPAGTX0501_010684-T1	45.11765	XANPAGTX0501_010684	mRNA	Xp_GTX0501_46	20975	22156		NA	hypothetical protein	NA	NA	NA	PF00067	IPR001128 Cytochrome P450;IPR002401 Cytochrome P450, E-class, group I;IPR017972 Cytochrome P450, conserved site;IPR036396 Cytochrome P450 superfamily	ENOG503NWJC	Q:(Q) Secondary metabolites biosynthesis, transport and catabolism	GO_function: GO:0016705 - oxidoreductase activity, acting on paired donors, with incorporation or reduction of molecular oxygen [Evidence IEA];GO_function: GO:0020037 - heme binding [Evidence IEA];GO_function: GO:0005506 - iron ion binding [Evidence IEA];GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	NA	NA	NA	NA	NA	NA	XANPAGTX0501_010684_T1_XANPAGTX0501_010684	NA	Q:(Q) Secondary metabolites biosynthesis, transport and catabolism	ENOG503NWJC	GO_function: GO:0005506 - iron ion binding [Evidence IEA], GO_function: GO:0016705 - oxidoreductase activity, acting on paired donors, with incorporation or reduction of molecular oxygen [Evidence IEA], GO_function: GO:0020037 - heme binding [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR001128 Cytochrome P450, IPR002401 Cytochrome P450, E-class, group I, IPR017972 Cytochrome P450, conserved site, IPR036396 Cytochrome P450 superfamily	PF00067	NA	NA

Most of these genes lack any annotation. There are three exceptions

Two are unclear:

• A protein assigned to IPR039559 Altered inheritance of mitochondria protein 6, PI-PLC-like catalytic domain. Function is unclear
• A protein assigned to IPR001128 Cytochrome P450

XANPAGTX0501_008856-T1 is interesting

• Has a F-box domain and a LRR (leucine-rich repeat) domain
• This review of fungal F-box proteins says that such proteins

act as scavengers in the cell, collecting “junk” proteins to deliver to a “waste processor,” called the SCF complex, to which they dock through their F-box domain. In the SCF complex, the junk proteins are marked with ubiquitin for “incineration” in the proteasome. F-box proteins do not act indiscriminately but recruit specific, often modified proteins to the SCF complex and in this way regulate the level of certain proteins in a cell. F-box proteins are found in all eukaryotes and display a large variety of functions. In fungi they are, for example, involved in control of the cell division cycle, glucose sensing, mitochondrial connectivity, and control of the circadian clock

• XANPAGTX0501_008856-T1 is from a lichen-enriched orthogroup
• Expression profile

plot_bootstrap(so, 
               target_id = "XANPAGTX0501_008856-T1", 
               units = "est_counts", 
               color_by = "condition")

Identified 1 gene that was highly expressed in all culture samples but not at all in the lichens

culture_unique<-counts_tab %>% filter(XBC2==0,XBA1==0,XSA2_2==0,XSC1==0,XSE2==0,XBE1==0,XTA2==0,XSC2==0,
  XSA2==0,XBA2==0,XBC1==0,XTA1==0,XSA1==0,XTC2==0,XTE2==0,XBE2==0,XMC2==0,
  S_21XB1>0,KS21XB1>0,S_21XB3>0,S_42XB1>0,S_42XB2>0,S_42XB3>0,
  KS48XB1>0,KS48XB2>0,KS48XB3>0,KS9XB1>0,KS9XB2>0,KS9XB3>0) %>% pivot_longer(-target_id,names_to="sample",values_to="counts") %>%
  filter(counts>0, sample !="MP_I",sample !="MP_II") %>% group_by(target_id) %>% summarise(avg_counts_culture=mean(as.numeric(counts))) %>%  
  left_join(funannot, by=c("target_id"="TranscriptID")) %>%
  select(-c(CDS.transcript,Translation,gDNA,mRNA))

culture_unique %>%
  kable(format = "html", col.names = colnames(culture_unique)) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

target_id	avg_counts_culture	GeneID	Feature	Contig	Start	Stop	Strand	Name	Product	Alias.Synonyms	EC_number	BUSCO	PFAM	InterPro	EggNog	COG	GO.Terms	Secreted	Membrane	Protease	CAZyme	antiSMASH	Notes	ProtID	CAZyme_new	COG_new	EggNog_new	GO.Terms_new	InterPro_new	PFAM_new	Protease_new	Secreted_new	KO
XANPAGTX0501_008359-T2	967.2169	XANPAGTX0501_008359	mRNA	Xp_GTX0501_15	271800	273051		NA	hypothetical protein	NA	NA	NA	PF03881	IPR011009 Protein kinase-like domain superfamily;IPR016477 Fructosamine/Ketosamine-3-kinase	ENOG503P2EP	G:(G) Carbohydrate transport and metabolism	NA	NA	NA	NA	NA	NA	NA	XANPAGTX0501_008359_T2_XANPAGTX0501_008359	NA	G:(G) Carbohydrate transport and metabolism	ENOG503NZHR, ENOG503P2EP	NA	IPR011009 Protein kinase-like domain superfamily, IPR016477 Fructosamine/Ketosamine-3-kinase	PF03881	NA	NA

According to InterPro, this protein is linked to protein repair

4. Investigate selected genes

4.1. Both gene models from the MAT-1-2-1 are upregulated in lichens

plot_bootstrap(so, 
               target_id = "XANPAGTX0501_002103-T1", 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = "XANPAGTX0501_002104-T1", 
               units = "est_counts", 
               color_by = "condition")

4.2. G-alpha proteins

• Of six proteins identified as G-alpha, none are in the DGE list. 4 have qval <0.05, but their b values are all between 0 and 1

galpha<-funannot %>% filter(grepl("IPR001019",InterPro_new))

sig %>% filter(target_id %in% galpha$TranscriptID)

## # A tibble: 5 × 12
##   target_id        pval     qval     b   se_b mean_obs var_obs tech_var sigma_sq
##   <chr>           <dbl>    <dbl> <dbl>  <dbl>    <dbl>   <dbl>    <dbl>    <dbl>
## 1 XANPAGTX050… 2.19e-14 3.18e-13 0.625 0.0819     8.08  0.130  0.000966   0.0323
## 2 XANPAGTX050… 6.74e- 9 4.96e- 8 0.582 0.100      7.59  0.153  0.000548   0.0702
## 3 XANPAGTX050… 4.12e- 4 1.26e- 3 0.491 0.139      7.97  0.192  0.00126    0.135 
## 4 XANPAGTX050… 2.57e- 3 6.48e- 3 0.233 0.0771     7.46  0.0288 0.000600   0.0152
## 5 XANPAGTX050… 2.58e- 2 4.90e- 2 0.210 0.0941     7.16  0.0712 0.000799   0.0615
## # ℹ 3 more variables: smooth_sigma_sq <dbl>, final_sigma_sq <dbl>, change <chr>

4.3. Multicellularity-related genes

• Use a review by Nagy et al. to compile a list of gene families/functions potentially involved in fungal multicellularity
  • Lists IDs in three databases: InterPRo, CAZy, and KEGG
  • Includes cell wall remodeling/biosynthesis, transcription factors, lipid metabolism genes, signalling pathways, etc
  • The whole table is in analysis_and_temp_files/08_dge_culture_lichen/multicellularity.txt
• Among the Xanpa annotation, 1552 genes belong to potentially multicellularity-involved families

mult_list<-read.delim2("../analysis_and_temp_files/08_dge_culture_lichen/multicellularity.txt")
#select genes that come from one of the categories of interest

ips_selected<-ips_df %>% mutate(ID=gsub( " .*$", "", InterPro_new)) %>% inner_join(mult_list,relationship = "many-to-many") %>% select(-c(InterPro_new,short_term))
ko_cazy_selected<-funannot %>% select(TranscriptID,KO,CAZyme_new) %>% 
  pivot_longer(-TranscriptID,names_to = "Annotation",values_to = "ID") %>% inner_join(mult_list,relationship = "many-to-many") %>% select(-Annotation)
mult_gene_table<-rbind(ips_selected,ko_cazy_selected)  
mult_gene_list<-unique(mult_gene_table$TranscriptID)

• Of them, 176 are deferentially expressed

mult_sig<-sig %>% filter(target_id %in% mult_gene_list)
mult_sig %>% group_by(change) %>% summarise(n=n())

## # A tibble: 3 × 2
##   change        n
##   <chr>     <int>
## 1 culture      60
## 2 lichen      116
## 3 low_logFC   650

• In lichen-upregulated genes, only 9.7890295% come from potentially multicellularity-related

mult_gene_table_lichen<-mult_gene_table %>% left_join(sig, by = c("TranscriptID"="target_id")) %>% 
  filter(change=="lichen") %>% arrange(Function) %>% arrange(Function_type) %>% left_join(funannot %>% select(TranscriptID,Product,CAZyme_new,COG_new,EggNog_new,GO.Terms_new,InterPro_new,PFAM_new,Protease_new,Secreted_new,KO))
mult_gene_table_lichen %>%
  kable(format = "html", col.names = colnames(mult_gene_table_lichen)) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

TranscriptID	ID	Annotation_type	Description	Function	Function_type	pval	qval	b	se_b	mean_obs	var_obs	tech_var	sigma_sq	smooth_sigma_sq	final_sigma_sq	change	Product	CAZyme_new	COG_new	EggNog_new	GO.Terms_new	InterPro_new	PFAM_new	Protease_new	Secreted_new	KO
XANPAGTX0501_002098-T1	IPR000504	IPR	RNA recognition motif domain	RNA binding proteins	Expression regulation	0.0000000	0.0000000	-1.180724	0.1849698	6.7305958	0.5823253	0.0014043	0.2392723	0.0548931	0.2392723	lichen	hypothetical protein	NA	NA	NA	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA]	IPR000504 RNA recognition motif domain, IPR012677 Nucleotide-binding alpha-beta plait domain superfamily, IPR035979 RNA-binding domain superfamily	PF00076	NA	NA
XANPAGTX0501_002123-T1	IPR000504	IPR	RNA recognition motif domain	RNA binding proteins	Expression regulation	0.0000000	0.0000000	-1.409280	0.2115689	5.5670492	0.8025913	0.0052488	0.3096244	0.1280387	0.3096244	lichen	hypothetical protein	NA	A:(A) RNA processing and modification	ENOG503NV3Z	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA], GO_function: GO:0003968 - RNA-directed 5’-3’ RNA polymerase activity [Evidence IEA]	IPR000504 RNA recognition motif domain, IPR007855 RNA-dependent RNA polymerase, eukaryotic-type, IPR035979 RNA-binding domain superfamily	PF00076, PF05183	NA	NA	K11699
XANPAGTX0501_004217-T1	IPR000504	IPR	RNA recognition motif domain	RNA binding proteins	Expression regulation	0.0000226	0.0000904	-1.121617	0.2646667	7.1794784	0.7912122	0.0009846	0.4917702	0.0435134	0.4917702	lichen	hypothetical protein	NA	A:(A) RNA processing and modification	ENOG503NWWZ	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA]	IPR000504 RNA recognition motif domain, IPR012677 Nucleotide-binding alpha-beta plait domain superfamily, IPR035979 RNA-binding domain superfamily	PF00076	NA	NA	K24990
XANPAGTX0501_005177-T1	IPR001313	IPR	Pumilio RNA-binding repeat	RNA binding proteins	Expression regulation	0.0000000	0.0000000	-1.397992	0.1803231	6.4929278	0.7115694	0.0018845	0.2268518	0.0644402	0.2268518	lichen	hypothetical protein	NA	J:(J) Translation, ribosomal structure and biogenesis	ENOG503NWID	GO_function: GO:0003723 - RNA binding [Evidence IEA]	IPR001313 Pumilio RNA-binding repeat, IPR011989 Armadillo-like helical, IPR016024 Armadillo-type fold, IPR033133 Pumilio homology domain, IPR033712 Pumilio, RNA binding domain	PF00806	NA	NA
XANPAGTX0501_008184-T1	IPR000504	IPR	RNA recognition motif domain	RNA binding proteins	Expression regulation	0.0000000	0.0000000	-1.446247	0.1469459	6.7102646	0.6719547	0.0017599	0.1501365	0.0556334	0.1501365	lichen	nucleolar protein	NA	A:(A) RNA processing and modification	ENOG503P21Q	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA]	IPR000504 RNA recognition motif domain, IPR035979 RNA-binding domain superfamily	PF00076	NA	NA	K14838
XANPAGTX0501_002123-T1	IPR007855	IPR	RNA-dependent RNA polymerase, eukaryotic-type	RNA interference	Expression regulation	0.0000000	0.0000000	-1.409280	0.2115689	5.5670492	0.8025913	0.0052488	0.3096244	0.1280387	0.3096244	lichen	hypothetical protein	NA	A:(A) RNA processing and modification	ENOG503NV3Z	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA], GO_function: GO:0003968 - RNA-directed 5’-3’ RNA polymerase activity [Evidence IEA]	IPR000504 RNA recognition motif domain, IPR007855 RNA-dependent RNA polymerase, eukaryotic-type, IPR035979 RNA-binding domain superfamily	PF00076, PF05183	NA	NA	K11699
XANPAGTX0501_003775-T1	IPR032474	IPR	Protein argonaute, N-terminal	RNA interference	Expression regulation	0.0000000	0.0000000	-2.274651	0.2772809	6.8421034	1.8214098	0.0107511	0.5300930	0.0509976	0.5300930	lichen	Protein argonaute	NA	J:(J) Translation, ribosomal structure and biogenesis	ENOG503NU0D	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA], GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR003100 PAZ domain, IPR003165 Piwi domain, IPR012337 Ribonuclease H-like superfamily, IPR014811 Argonaute, linker 1 domain, IPR032472 Argonaute linker 2 domain, IPR032473 Protein argonaute, Mid domain, IPR032474 Protein argonaute, N-terminal, IPR036085 PAZ domain superfamily, IPR036397 Ribonuclease H superfamily	PF02170, PF02171, PF08699, PF16486, PF16487, PF16488	NA	NA	K11593
XANPAGTX0501_003775-T2	IPR032474	IPR	Protein argonaute, N-terminal	RNA interference	Expression regulation	0.0000205	0.0000828	-2.057983	0.4831465	5.8134652	2.6474578	0.0412204	1.6008430	0.1064615	1.6008430	lichen	Protein argonaute, variant 2	NA	J:(J) Translation, ribosomal structure and biogenesis	ENOG503NU0D	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA], GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR003100 PAZ domain, IPR003165 Piwi domain, IPR012337 Ribonuclease H-like superfamily, IPR014811 Argonaute, linker 1 domain, IPR032472 Argonaute linker 2 domain, IPR032473 Protein argonaute, Mid domain, IPR032474 Protein argonaute, N-terminal, IPR036085 PAZ domain superfamily, IPR036397 Ribonuclease H superfamily	PF02170, PF02171, PF08699, PF16486, PF16487, PF16488	NA	NA	K11593
XANPAGTX0501_000175-T1	IPR021858	IPR	Fungal transcription factor	Transcription factors	Expression regulation	0.0000000	0.0000000	-1.425105	0.1020771	8.0627509	0.5809117	0.0003763	0.0729211	0.0460046	0.0729211	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503P1GT	NA	IPR021858 Fungal transcription factor	PF11951	NA	NA	K09245
XANPAGTX0501_000407-T1	IPR007219	IPR	Transcription factor domain, fungi	Transcription factors	Expression regulation	0.0000001	0.0000008	-4.965225	0.9414857	2.2175021	12.2063692	0.0374838	6.1978489	1.0508282	6.1978489	lichen	elongation factor EF-1 gamma subunit	NA	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NUBV	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0003677 - DNA binding [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006351 - transcription, DNA-templated [Evidence IEA]	IPR004046 Glutathione S-transferase, C-terminal, IPR007219 Transcription factor domain, fungi, IPR010987 Glutathione S-transferase, C-terminal-like, IPR036249 Thioredoxin-like superfamily, IPR036282 Glutathione S-transferase, C-terminal domain superfamily	PF00043, PF04082	NA	NA
XANPAGTX0501_000420-T1	IPR013087	IPR	Zinc finger C2H2-type	Transcription factors	Expression regulation	0.0000003	0.0000019	-1.619168	0.3172708	5.7170109	1.3414620	0.0058413	0.7022550	0.1143416	0.7022550	lichen	hypothetical protein	NA	NA	NA	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA]	IPR013087 Zinc finger C2H2-type	NA	NA	NA
XANPAGTX0501_000908-T1	IPR036864	IPR	Zn(2)-C6 fungal-type DNA-binding domain superfamily	Transcription factors	Expression regulation	0.0000000	0.0000000	-2.580872	0.2388253	6.7091912	2.0603276	0.0029386	0.3982908	0.0556726	0.3982908	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503P38P, ENOG503P3FF, ENOG503P6MQ	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR011008 Dimeric alpha-beta barrel, IPR025444 Monooxygenase af470-like, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00172, PF13826	NA	NA
XANPAGTX0501_000984-T1	IPR013087	IPR	Zinc finger C2H2-type	Transcription factors	Expression regulation	0.0000064	0.0000287	-3.164451	0.7010526	1.1618760	5.8495671	0.0699227	3.3873482	1.3805344	3.3873482	lichen	hypothetical protein	NA	NA	NA	GO_component: GO:0005871 - kinesin complex [Evidence IEA], GO_function: GO:0003676 - nucleic acid binding [Evidence IEA], GO_function: GO:0003777 - microtubule motor activity [Evidence IEA], GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR002151 Kinesin light chain, IPR011990 Tetratricopeptide-like helical domain superfamily, IPR013026 None, IPR013087 Zinc finger C2H2-type, IPR019734 Tetratricopeptide repeat	PF07721, PF13176, PF13181, PF13374, PF13424, PF13432	NA	NA	K19360
XANPAGTX0501_001247-T1	IPR013087	IPR	Zinc finger C2H2-type	Transcription factors	Expression regulation	0.0000000	0.0000000	-2.397327	0.2645924	8.6955333	1.9187617	0.0003628	0.4921154	0.0593459	0.4921154	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503P6RV	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA]	IPR013087 Zinc finger C2H2-type, IPR036236 Zinc finger C2H2 superfamily	PF00096, PF12874	NA	NA
XANPAGTX0501_001515-T1	IPR013087	IPR	Zinc finger C2H2-type	Transcription factors	Expression regulation	0.0000000	0.0000000	-1.263312	0.1630561	5.7990387	0.5813032	0.0041515	0.1828763	0.1075978	0.1828763	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503P3AU	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA]	IPR013087 Zinc finger C2H2-type	NA	NA	NA
XANPAGTX0501_001955-T1	IPR036864	IPR	Zn(2)-C6 fungal-type DNA-binding domain superfamily	Transcription factors	Expression regulation	0.0000006	0.0000034	-2.440667	0.4894590	2.6893033	3.1216145	0.0907717	1.5944802	0.8812435	1.5944802	lichen	hypothetical protein	NA	E:(E) Amino acid transport and metabolism	ENOG503P05H	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0005515 - protein binding [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_function: GO:0016407 - acetyltransferase activity [Evidence IEA], GO_function: GO:0016740 - transferase activity [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR001451 Hexapeptide repeat, IPR002110 Ankyrin repeat, IPR011004 Trimeric LpxA-like superfamily, IPR018357 Hexapeptide transferase, conserved site, IPR020683 Domain of unknown function DUF3447, IPR024688 Maltose/galactoside acetyltransferase, IPR036770 Ankyrin repeat-containing domain superfamily, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00023, PF00132, PF00172, PF12464, PF12796, PF13606, PF13637, PF14602	NA	NA
XANPAGTX0501_001958-T1	IPR001356	IPR	Homeobox domain	Transcription factors	Expression regulation	0.0000084	0.0000370	-1.992967	0.4474329	1.6517548	2.3333489	0.1675110	1.2174290	1.2407658	1.2407658	lichen	hypothetical protein	NA	K:(K) Transcription	ENOG503NU1B	GO_function: GO:0003677 - DNA binding [Evidence IEA], GO_function: GO:0043565 - sequence-specific DNA binding [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001356 Homeobox domain, IPR009057 Homeobox-like domain superfamily, IPR017970 Homeobox, conserved site	PF00046	NA	NA
XANPAGTX0501_002427-T1	IPR036864	IPR	Zn(2)-C6 fungal-type DNA-binding domain superfamily	Transcription factors	Expression regulation	0.0000008	0.0000040	-1.786972	0.3612022	4.4657802	1.6872407	0.0126518	0.9051165	0.3124016	0.9051165	lichen	hypothetical protein	NA	NA	NA	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00172, PF08493	NA	NA
XANPAGTX0501_002947-T1	IPR013083	IPR	Zinc finger, RING/FYVE/PHD-type	Transcription factors	Expression regulation	0.0000000	0.0000000	-1.534891	0.2355584	6.0934408	0.9682616	0.0032977	0.3870300	0.0869775	0.3870300	lichen	hypothetical protein	NA	NA	NA	GO_function: GO:0005524 - ATP binding [Evidence IEA], GO_function: GO:0046872 - metal ion binding [Evidence IEA]	IPR000330 SNF2, N-terminal, IPR001650 Helicase, C-terminal, IPR001841 Zinc finger, RING-type, IPR013083 Zinc finger, RING/FYVE/PHD-type, IPR014001 Helicase superfamily 1/2, ATP-binding domain, IPR017907 Zinc finger, RING-type, conserved site, IPR018957 Zinc finger, C3HC4 RING-type, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR038718 SNF2-like, N-terminal domain superfamily	PF00097, PF00176, PF00271	NA	NA
XANPAGTX0501_004715-T1	IPR036864	IPR	Zn(2)-C6 fungal-type DNA-binding domain superfamily	Transcription factors	Expression regulation	0.0000008	0.0000043	-1.034993	0.2097128	8.2688977	0.5674459	0.0003167	0.3090561	0.0494292	0.3090561	lichen	Transcriptional regulator of nonfermentable carbon utilization	NA	K:(K) Transcription	ENOG503NWT9	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	NA	NA	NA
XANPAGTX0501_004992-T1	IPR013087	IPR	Zinc finger C2H2-type	Transcription factors	Expression regulation	0.0000000	0.0000000	-5.764706	0.4337961	2.7684930	9.6253515	0.0379985	1.2857439	0.8525623	1.2857439	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503P2PR	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA]	IPR013087 Zinc finger C2H2-type	NA	NA	NA
XANPAGTX0501_005300-T1	IPR007219	IPR	Transcription factor domain, fungi	Transcription factors	Expression regulation	0.0000000	0.0000000	-1.676816	0.2195573	4.4421064	0.9313211	0.0208903	0.2123714	0.3182097	0.3182097	lichen	hypothetical protein	NA	B:(B) Chromatin structure and dynamics	ENOG503NX03	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0003677 - DNA binding [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006351 - transcription, DNA-templated [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR007219 Transcription factor domain, fungi, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00172, PF04082	NA	NA
XANPAGTX0501_005300-T1	IPR036864	IPR	Zn(2)-C6 fungal-type DNA-binding domain superfamily	Transcription factors	Expression regulation	0.0000000	0.0000000	-1.676816	0.2195573	4.4421064	0.9313211	0.0208903	0.2123714	0.3182097	0.3182097	lichen	hypothetical protein	NA	B:(B) Chromatin structure and dynamics	ENOG503NX03	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0003677 - DNA binding [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006351 - transcription, DNA-templated [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR007219 Transcription factor domain, fungi, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00172, PF04082	NA	NA
XANPAGTX0501_005593-T1	IPR036864	IPR	Zn(2)-C6 fungal-type DNA-binding domain superfamily	Transcription factors	Expression regulation	0.0000054	0.0000246	-1.214092	0.2668317	4.9475935	0.8532820	0.0102803	0.4905689	0.2111149	0.4905689	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503P38P, ENOG503P3FF, ENOG503P6MQ	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR011008 Dimeric alpha-beta barrel, IPR025444 Monooxygenase af470-like, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00172, PF13826	NA	NA
XANPAGTX0501_006203-T1	IPR013083	IPR	Zinc finger, RING/FYVE/PHD-type	Transcription factors	Expression regulation	0.0000000	0.0000000	-2.316940	0.3110455	3.4826578	1.9648390	0.0790759	0.5599209	0.6015053	0.6015053	lichen	hypothetical protein	NA	O:(O) Posttranslational modification, protein turnover, chaperones, S:(S) Function unknown	ENOG503NVJG, ENOG50KOG1812	NA	IPR001841 Zinc finger, RING-type, IPR002867 IBR domain, IPR013083 Zinc finger, RING/FYVE/PHD-type, IPR017907 Zinc finger, RING-type, conserved site	PF01485	NA	NA
XANPAGTX0501_006448-T1	IPR013083	IPR	Zinc finger, RING/FYVE/PHD-type	Transcription factors	Expression regulation	0.0030050	0.0074422	-1.199765	0.4043394	2.3478752	0.9633655	0.1455887	0.4784313	1.0044813	1.0044813	lichen	hypothetical protein	NA	NA	NA	NA	IPR001841 Zinc finger, RING-type, IPR013083 Zinc finger, RING/FYVE/PHD-type	NA	NA	NA
XANPAGTX0501_006931-T1	IPR013087	IPR	Zinc finger C2H2-type	Transcription factors	Expression regulation	0.0000000	0.0000000	-1.314529	0.2201759	4.9171457	0.7629592	0.0100321	0.3309816	0.2165319	0.3309816	lichen	hypothetical protein	NA	NA	NA	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA]	IPR013087 Zinc finger C2H2-type	PF12874	NA	NA
XANPAGTX0501_007310-T1	IPR013087	IPR	Zinc finger C2H2-type	Transcription factors	Expression regulation	0.0000057	0.0000261	-3.914334	0.8627371	1.6014626	8.8982508	0.0538869	5.1819866	1.2563905	5.1819866	lichen	hypothetical protein	NA	NA	NA	GO_component: GO:0005871 - kinesin complex [Evidence IEA], GO_function: GO:0003676 - nucleic acid binding [Evidence IEA], GO_function: GO:0003777 - microtubule motor activity [Evidence IEA], GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR002151 Kinesin light chain, IPR011990 Tetratricopeptide-like helical domain superfamily, IPR013026 None, IPR013087 Zinc finger C2H2-type, IPR019734 Tetratricopeptide repeat	PF07721, PF13176, PF13181, PF13374, PF13424, PF13432	NA	NA
XANPAGTX0501_007754-T1	IPR013087	IPR	Zinc finger C2H2-type	Transcription factors	Expression regulation	0.0006867	0.0019895	-2.683149	0.7903623	0.8797330	6.0459986	0.1947670	4.1994814	1.4460749	4.1994814	lichen	hypothetical protein	NA	A:(A) RNA processing and modification	ENOG503NVZ2	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA]	IPR013087 Zinc finger C2H2-type, IPR019447 DNA/RNA-binding protein Kin17, WH-like domain, IPR036236 Zinc finger C2H2 superfamily, IPR038254 DNA/RNA-binding protein KIN17, WH-like domain superfamily	PF10357, PF12171, PF12874	NA	NA	K13102
XANPAGTX0501_009436-T1	IPR013083	IPR	Zinc finger, RING/FYVE/PHD-type	Transcription factors	Expression regulation	0.0000000	0.0000000	-1.317000	0.1684260	6.7814389	0.6281810	0.0017142	0.1978352	0.0530697	0.1978352	lichen	hypothetical protein	NA	K:(K) Transcription, L:(L) Replication, recombination and repair	ENOG503NTZ9	GO_function: GO:0005524 - ATP binding [Evidence IEA]	IPR000330 SNF2, N-terminal, IPR001650 Helicase, C-terminal, IPR001841 Zinc finger, RING-type, IPR013083 Zinc finger, RING/FYVE/PHD-type, IPR014001 Helicase superfamily 1/2, ATP-binding domain, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR038718 SNF2-like, N-terminal domain superfamily	PF00097, PF00176, PF00271, PF13445, PF13639, PF13920, PF13923	NA	NA	K15711
XANPAGTX0501_010366-T1	IPR013087	IPR	Zinc finger C2H2-type	Transcription factors	Expression regulation	0.0000000	0.0000000	-1.609971	0.2095510	6.8304354	0.9490572	0.0015725	0.3073230	0.0513842	0.3073230	lichen	hypothetical protein	AA9	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NYCR, ENOG503Q4YD	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA], GO_function: GO:0008061 - chitin binding [Evidence IEA]	IPR001002 Chitin-binding, type 1, IPR005103 Auxiliary Activity family 9, IPR013087 Zinc finger C2H2-type, IPR018371 Chitin-binding, type 1, conserved site, IPR036861 Endochitinase-like superfamily	PF00187, PF03443	NA	SignalP(1-21,cutsite=ASA-HT,prob=0.7581), SignalP(1-21,cutsite=VSA-HG,prob=0.4970)
XANPAGTX0501_001061-T1	IPR013149	IPR	Alcohol dehydrogenase-like, C-terminal	Acetyl-CoA production and metabolism	Fungal multicellularity	0.0009257	0.0026006	-1.037850	0.3133439	6.0351163	0.9366190	0.0037097	0.6869666	0.0906680	0.6869666	lichen	hypothetical protein	NA	Q:(Q) Secondary metabolites biosynthesis, transport and catabolism	ENOG503NUUT	GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR002328 Alcohol dehydrogenase, zinc-type, conserved site, IPR011032 GroES-like superfamily, IPR013149 Alcohol dehydrogenase-like, C-terminal, IPR013154 Alcohol dehydrogenase-like, N-terminal, IPR020843 Polyketide synthase, enoylreductase domain, IPR036291 NAD(P)-binding domain superfamily	PF00107, PF08240	NA	NA
XANPAGTX0501_002156-T1	IPR013149	IPR	Alcohol dehydrogenase-like, C-terminal	Acetyl-CoA production and metabolism	Fungal multicellularity	0.0000000	0.0000000	-3.256431	0.2782381	3.8777351	2.9364022	0.0696283	0.2127120	0.4749563	0.4749563	lichen	quinone oxidoreductase	NA	S:(S) Function unknown	ENOG503NWMF	GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR011032 GroES-like superfamily, IPR013149 Alcohol dehydrogenase-like, C-terminal, IPR020843 Polyketide synthase, enoylreductase domain, IPR036291 NAD(P)-binding domain superfamily, IPR041694 Oxidoreductase, N-terminal domain	PF00107, PF13602, PF16884	NA	NA
XANPAGTX0501_005604-T1	IPR015590	IPR	Aldehyde dehydrogenase domain	Acetyl-CoA production and metabolism	Fungal multicellularity	0.0000000	0.0000000	-1.078674	0.1601407	6.2817591	0.4662738	0.0024796	0.1779199	0.0757764	0.1779199	lichen	mitochondrial aldehyde dehydrogenase	NA	E:(E) Amino acid transport and metabolism	ENOG503NW4N	GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_function: GO:0016620 - oxidoreductase activity, acting on the aldehyde or oxo group of donors, NAD or NADP as acceptor [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR015590 Aldehyde dehydrogenase domain, IPR016161 Aldehyde/histidinol dehydrogenase, IPR016162 Aldehyde dehydrogenase, N-terminal, IPR016163 Aldehyde dehydrogenase, C-terminal, IPR029510 Aldehyde dehydrogenase, glutamic acid active site	PF00171	NA	NA	K00128
XANPAGTX0501_008656-T1	IPR001765	IPR	Carbonic anhydrase	Acetyl-CoA production and metabolism	Fungal multicellularity	0.0000000	0.0000000	-1.100140	0.1571460	7.7824764	0.4715789	0.0005070	0.1732085	0.0425282	0.1732085	lichen	hypothetical protein	NA	P:(P) Inorganic ion transport and metabolism	ENOG503P2HN	GO_function: GO:0004089 - carbonate dehydratase activity [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA]	IPR001765 Carbonic anhydrase, IPR036874 Carbonic anhydrase superfamily	PF00484	NA	NA	K01673
XANPAGTX0501_005597-T1	IPR032788	IPR	Glycogen debranching enzyme, central domain	Carbohydrate storage	Fungal multicellularity	0.0000000	0.0000000	-1.979785	0.2652912	8.1732481	1.4621157	0.0004607	0.4946222	0.0477428	0.4946222	lichen	bifunctional 4-alpha-glucanotransferase/amylo-alpha-1,6-glucosidase	GH133	G:(G) Carbohydrate transport and metabolism	ENOG503NU7F	GO_function: GO:0003824 - catalytic activity [Evidence IEA], GO_function: GO:0004134 - 4-alpha-glucanotransferase activity [Evidence IEA], GO_function: GO:0004135 - amylo-alpha-1,6-glucosidase activity [Evidence IEA], GO_process: GO:0005978 - glycogen biosynthetic process [Evidence IEA]	IPR006421 Glycogen debranching enzyme, metazoa, IPR008928 Six-hairpin glycosidase superfamily, IPR012341 Six-hairpin glycosidase-like superfamily, IPR017853 Glycoside hydrolase superfamily, IPR029436 Eukaryotic glycogen debranching enzyme, N-terminal domain, IPR032788 Glycogen debranching enzyme, central domain, IPR032790 Glycogen debranching enzyme, C-terminal, IPR032792 Glycogen debranching enzyme, glucanotransferase domain	PF06202, PF14699, PF14701, PF14702	NA	NA	K01196
XANPAGTX0501_000647-T1	IPR000571	IPR	Zinc finger, CCCH-type	Cell division, proliferation and growth	Fungal multicellularity	0.0000000	0.0000000	-4.496178	0.3846374	2.9525771	6.0823541	0.1027690	0.9379539	0.7861878	0.9379539	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503P01Q, ENOG503P1HJ, ENOG503PEAA	GO_function: GO:0046872 - metal ion binding [Evidence IEA]	IPR000571 Zinc finger, CCCH-type	NA	NA	NA
XANPAGTX0501_000836-T2	IPR006910	IPR	Rad21/Rec8-like protein, N-terminal	Cell division, proliferation and growth	Fungal multicellularity	0.0000000	0.0000002	-1.085090	0.1972410	5.6051017	0.5597009	0.1196526	0.1540171	0.1243830	0.1540171	lichen	R8 protein, variant 2	NA	D:(D) Cell cycle control, cell division, chromosome partitioning	ENOG503NY2J	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR006910 Rad21/Rec8-like protein, N-terminal	PF04825	NA	NA	K12780
XANPAGTX0501_000836-T3	IPR006910	IPR	Rad21/Rec8-like protein, N-terminal	Cell division, proliferation and growth	Fungal multicellularity	0.0000093	0.0000404	-2.453886	0.5535294	3.5156657	3.5911573	0.7253577	1.4299715	0.5904966	1.4299715	lichen	R8 protein, variant 3	NA	D:(D) Cell cycle control, cell division, chromosome partitioning	ENOG503NY2J	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR006910 Rad21/Rec8-like protein, N-terminal	PF04825	NA	NA
XANPAGTX0501_002153-T1	IPR001650	IPR	Helicase, C-terminal	Cell division, proliferation and growth	Fungal multicellularity	0.0000000	0.0000000	-1.561455	0.2020442	5.0324025	0.8894432	0.0100075	0.2771533	0.1967239	0.2771533	lichen	hypothetical protein	NA	L:(L) Replication, recombination and repair	ENOG503NVEK	GO_function: GO:0005515 - protein binding [Evidence IEA], GO_function: GO:0005524 - ATP binding [Evidence IEA]	IPR000330 SNF2, N-terminal, IPR001650 Helicase, C-terminal, IPR003892 Ubiquitin system component CUE, IPR009060 UBA-like superfamily, IPR014001 Helicase superfamily 1/2, ATP-binding domain, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR038718 SNF2-like, N-terminal domain superfamily	PF00176, PF00271, PF04851	NA	NA
XANPAGTX0501_002213-T1	IPR001650	IPR	Helicase, C-terminal	Cell division, proliferation and growth	Fungal multicellularity	0.0000000	0.0000000	-3.437733	0.2593037	5.5245879	3.4251508	0.0121727	0.4608145	0.1322735	0.4608145	lichen	hypothetical protein	NA	A:(A) RNA processing and modification	ENOG503NUBU	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA], GO_function: GO:0005524 - ATP binding [Evidence IEA]	IPR000629 ATP-dependent RNA helicase DEAD-box, conserved site, IPR001650 Helicase, C-terminal, IPR011545 DEAD/DEAH box helicase domain, IPR014001 Helicase superfamily 1/2, ATP-binding domain, IPR014014 RNA helicase, DEAD-box type, Q motif, IPR027417 P-loop containing nucleoside triphosphate hydrolase	PF00270, PF00271	NA	NA
XANPAGTX0501_002947-T1	IPR001650	IPR	Helicase, C-terminal	Cell division, proliferation and growth	Fungal multicellularity	0.0000000	0.0000000	-1.534891	0.2355584	6.0934408	0.9682616	0.0032977	0.3870300	0.0869775	0.3870300	lichen	hypothetical protein	NA	NA	NA	GO_function: GO:0005524 - ATP binding [Evidence IEA], GO_function: GO:0046872 - metal ion binding [Evidence IEA]	IPR000330 SNF2, N-terminal, IPR001650 Helicase, C-terminal, IPR001841 Zinc finger, RING-type, IPR013083 Zinc finger, RING/FYVE/PHD-type, IPR014001 Helicase superfamily 1/2, ATP-binding domain, IPR017907 Zinc finger, RING-type, conserved site, IPR018957 Zinc finger, C3HC4 RING-type, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR038718 SNF2-like, N-terminal domain superfamily	PF00097, PF00176, PF00271	NA	NA
XANPAGTX0501_003775-T1	IPR012337	IPR	Ribonuclease H-like superfamily	Cell division, proliferation and growth	Fungal multicellularity	0.0000000	0.0000000	-2.274651	0.2772809	6.8421034	1.8214098	0.0107511	0.5300930	0.0509976	0.5300930	lichen	Protein argonaute	NA	J:(J) Translation, ribosomal structure and biogenesis	ENOG503NU0D	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA], GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR003100 PAZ domain, IPR003165 Piwi domain, IPR012337 Ribonuclease H-like superfamily, IPR014811 Argonaute, linker 1 domain, IPR032472 Argonaute linker 2 domain, IPR032473 Protein argonaute, Mid domain, IPR032474 Protein argonaute, N-terminal, IPR036085 PAZ domain superfamily, IPR036397 Ribonuclease H superfamily	PF02170, PF02171, PF08699, PF16486, PF16487, PF16488	NA	NA	K11593
XANPAGTX0501_003775-T2	IPR012337	IPR	Ribonuclease H-like superfamily	Cell division, proliferation and growth	Fungal multicellularity	0.0000205	0.0000828	-2.057983	0.4831465	5.8134652	2.6474578	0.0412204	1.6008430	0.1064615	1.6008430	lichen	Protein argonaute, variant 2	NA	J:(J) Translation, ribosomal structure and biogenesis	ENOG503NU0D	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA], GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR003100 PAZ domain, IPR003165 Piwi domain, IPR012337 Ribonuclease H-like superfamily, IPR014811 Argonaute, linker 1 domain, IPR032472 Argonaute linker 2 domain, IPR032473 Protein argonaute, Mid domain, IPR032474 Protein argonaute, N-terminal, IPR036085 PAZ domain superfamily, IPR036397 Ribonuclease H superfamily	PF02170, PF02171, PF08699, PF16486, PF16487, PF16488	NA	NA	K11593
XANPAGTX0501_004104-T1	IPR001214	IPR	SET domain	Cell division, proliferation and growth	Fungal multicellularity	0.0000000	0.0000000	-3.030921	0.3772536	4.3358886	3.2733277	0.0238234	0.9773259	0.3451420	0.9773259	lichen	N-lysine methyltransferase smyd2	NA	B:(B) Chromatin structure and dynamics	ENOG503BJFF	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR001214 SET domain, IPR011990 Tetratricopeptide-like helical domain superfamily	PF00856	NA	NA
XANPAGTX0501_004628-T1	IPR012337	IPR	Ribonuclease H-like superfamily	Cell division, proliferation and growth	Fungal multicellularity	0.0000000	0.0000000	-2.032220	0.2987673	4.8709032	1.6430517	0.0182317	0.6096795	0.2250137	0.6096795	lichen	hypothetical protein	NA	L:(L) Replication, recombination and repair	ENOG503P5AI	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA], GO_function: GO:0004523 - RNA-DNA hybrid ribonuclease activity [Evidence IEA]	IPR002156 Ribonuclease H domain, IPR012337 Ribonuclease H-like superfamily, IPR036397 Ribonuclease H superfamily	PF00075	NA	NA	K03469
XANPAGTX0501_005143-T1	IPR012337	IPR	Ribonuclease H-like superfamily	Cell division, proliferation and growth	Fungal multicellularity	0.0000965	0.0003392	-1.504594	0.3858815	3.7596947	1.5787954	0.0401662	1.0073003	0.5114982	1.0073003	lichen	hypothetical protein	NA	L:(L) Replication, recombination and repair	ENOG503NYTC	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA], GO_function: GO:0004523 - RNA-DNA hybrid ribonuclease activity [Evidence IEA], GO_process: GO:0016070 - RNA metabolic process [Evidence IEA]	IPR004649 Ribonuclease H2, subunit A, IPR012337 Ribonuclease H-like superfamily, IPR023160 Ribonuclease HII, helix-loop-helix cap domain superfamily, IPR024567 Ribonuclease HII/HIII domain, IPR036397 Ribonuclease H superfamily	PF01351	NA	NA	K10743
XANPAGTX0501_009436-T1	IPR001650	IPR	Helicase, C-terminal	Cell division, proliferation and growth	Fungal multicellularity	0.0000000	0.0000000	-1.317000	0.1684260	6.7814389	0.6281810	0.0017142	0.1978352	0.0530697	0.1978352	lichen	hypothetical protein	NA	K:(K) Transcription, L:(L) Replication, recombination and repair	ENOG503NTZ9	GO_function: GO:0005524 - ATP binding [Evidence IEA]	IPR000330 SNF2, N-terminal, IPR001650 Helicase, C-terminal, IPR001841 Zinc finger, RING-type, IPR013083 Zinc finger, RING/FYVE/PHD-type, IPR014001 Helicase superfamily 1/2, ATP-binding domain, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR038718 SNF2-like, N-terminal domain superfamily	PF00097, PF00176, PF00271, PF13445, PF13639, PF13920, PF13923	NA	NA	K15711
XANPAGTX0501_000058-T1	IPR001461	IPR	Aspartic peptidase A1 family	Cell surface and cell wall proteins	Fungal multicellularity	0.0000000	0.0000000	-1.165441	0.1400048	5.5170620	0.4246687	0.0048435	0.0816796	0.1330417	0.1330417	lichen	Belongs to the peptidase A1	NA	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503BJZI	GO_function: GO:0004190 - aspartic-type endopeptidase activity [Evidence IEA], GO_process: GO:0006508 - proteolysis [Evidence IEA]	IPR001461 Aspartic peptidase A1 family, IPR001969 Aspartic peptidase, active site, IPR021109 Aspartic peptidase domain superfamily, IPR033121 Peptidase family A1 domain, IPR033876 Secreted aspartic endopeptidase	PF00026, PF14543	A01A	SignalP(1-20,cutsite=CLA-AE,prob=0.6923), SignalP(1-25,cutsite=VSA-LK,prob=0.4319)
XANPAGTX0501_000656-T1	IPR000772	IPR	Ricin B, lectin domain	Cell surface and cell wall proteins	Fungal multicellularity	0.0000000	0.0000000	-4.357565	0.4814432	5.9017838	6.3427509	0.0164185	1.6140872	0.0998084	1.6140872	lichen	hypothetical protein	NA	NA	NA	NA	IPR000772 Ricin B, lectin domain, IPR035992 Ricin B-like lectins	NA	NA	SignalP(1-20,cutsite=SFS-DI,prob=0.7168), SignalP(1-21,cutsite=VAS-LI,prob=0.3541), SignalP(1-24,cutsite=ASA-AI,prob=0.5941)
XANPAGTX0501_000731-T1	IPR001461	IPR	Aspartic peptidase A1 family	Cell surface and cell wall proteins	Fungal multicellularity	0.0005301	0.0015770	-1.218829	0.3517482	3.1167635	0.6369498	0.1426678	0.1308341	0.7276860	0.7276860	lichen	hypothetical protein	NA	NA	NA	GO_function: GO:0004190 - aspartic-type endopeptidase activity [Evidence IEA], GO_process: GO:0006508 - proteolysis [Evidence IEA]	IPR001461 Aspartic peptidase A1 family, IPR001969 Aspartic peptidase, active site, IPR021109 Aspartic peptidase domain superfamily, IPR033121 Peptidase family A1 domain	PF00026	A01A	SignalP(1-22,cutsite=AFA-LP,prob=0.8740)
XANPAGTX0501_003124-T1	IPR001461	IPR	Aspartic peptidase A1 family	Cell surface and cell wall proteins	Fungal multicellularity	0.0000001	0.0000005	-1.008637	0.1878909	7.5066395	0.4950593	0.0006687	0.2476697	0.0412267	0.2476697	lichen	hypothetical protein	NA	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503P2G1	GO_function: GO:0004190 - aspartic-type endopeptidase activity [Evidence IEA], GO_process: GO:0006508 - proteolysis [Evidence IEA]	IPR001461 Aspartic peptidase A1 family, IPR001969 Aspartic peptidase, active site, IPR021109 Aspartic peptidase domain superfamily, IPR033121 Peptidase family A1 domain, IPR034164 Pepsin-like domain	PF00026	A01A	SignalP(1-19,cutsite=IAG-AP,prob=0.5669)
XANPAGTX0501_005735-T1	IPR018824	IPR	Conidiation-specific protein 6	Cell surface and cell wall proteins	Fungal multicellularity	0.0004114	0.0012601	-1.470775	0.4163374	6.5748366	1.7192456	0.0027286	1.2166061	0.0607546	1.2166061	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503P6QX	NA	IPR018824 Conidiation-specific protein 6	PF10346	NA	NA
XANPAGTX0501_006283-T1	IPR000772	IPR	Ricin B, lectin domain	Cell surface and cell wall proteins	Fungal multicellularity	0.0000000	0.0000000	-1.624636	0.2179258	6.1319702	0.9852594	0.0033028	0.3307766	0.0846337	0.3307766	lichen	hypothetical protein	NA	NA	NA	NA	IPR000772 Ricin B, lectin domain, IPR035992 Ricin B-like lectins	NA	NA	SignalP(1-20,cutsite=SFS-DI,prob=0.7168), SignalP(1-21,cutsite=VAS-LI,prob=0.3541), SignalP(1-24,cutsite=ASA-AI,prob=0.5941)
XANPAGTX0501_007515-T1	IPR001461	IPR	Aspartic peptidase A1 family	Cell surface and cell wall proteins	Fungal multicellularity	0.0000000	0.0000000	-2.210135	0.1595195	7.0563543	1.3997999	0.0013946	0.1776080	0.0455049	0.1776080	lichen	hypothetical protein	NA	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NUDE, ENOG503NV31	GO_function: GO:0004190 - aspartic-type endopeptidase activity [Evidence IEA], GO_process: GO:0006508 - proteolysis [Evidence IEA]	IPR001461 Aspartic peptidase A1 family, IPR001969 Aspartic peptidase, active site, IPR021109 Aspartic peptidase domain superfamily, IPR033121 Peptidase family A1 domain, IPR034163 Aspergillopepsin-like catalytic domain	PF00026	A01A	SignalP(1-20,cutsite=VVA-AP,prob=0.8993), SignalP(1-28,cutsite=LRA-GN,prob=0.1255)
XANPAGTX0501_009310-T1	IPR032805	IPR	Wax synthase domain	Cell surface and cell wall proteins	Fungal multicellularity	0.0000000	0.0000000	-1.207676	0.2031951	4.6133699	0.5641894	0.0125546	0.1925432	0.2778869	0.2778869	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503PI83	NA	IPR032805 Wax synthase domain	PF13813	NA	NA
XANPAGTX0501_010170-T1	IPR000772	IPR	Ricin B, lectin domain	Cell surface and cell wall proteins	Fungal multicellularity	0.0000000	0.0000000	-5.061039	0.6249441	5.3041424	9.0843083	0.0535647	2.6937891	0.1573140	2.6937891	lichen	hypothetical protein	NA	NA	NA	NA	IPR000772 Ricin B, lectin domain, IPR035992 Ricin B-like lectins	NA	NA	SignalP(1-20,cutsite=SFS-DI,prob=0.7168), SignalP(1-21,cutsite=VAS-LI,prob=0.3541), SignalP(1-24,cutsite=ASA-AI,prob=0.5941)
XANPAGTX0501_006327-T1	IPR018466	IPR	Yeast cell wall synthesis Kre9/Knh1-like, N-terminal	Cell wall biosynthesis	Fungal multicellularity	0.0000000	0.0000000	-3.436352	0.3951956	7.1358779	4.0260768	0.0026336	1.0960090	0.0441646	1.0960090	lichen	hypothetical protein	NA	NA	NA	NA	IPR018466 Yeast cell wall synthesis Kre9/Knh1-like, N-terminal	PF10342	NA	SignalP(1-21,cutsite=SLA-GP,prob=0.8907)
XANPAGTX0501_006432-T1	IPR000028	IPR	Chloroperoxidase	Cell wall misc	Fungal multicellularity	0.0000000	0.0000000	-1.503512	0.1717140	6.5487759	0.7679301	0.0023704	0.2050463	0.0618744	0.2050463	lichen	hypothetical protein	NA	E:(E) Amino acid transport and metabolism	ENOG503P55P	GO_function: GO:0004601 - peroxidase activity [Evidence IEA]	IPR000028 Chloroperoxidase, IPR036851 Chloroperoxidase-like superfamily	PF01328	NA	NA
XANPAGTX0501_008027-T1	IPR000028	IPR	Chloroperoxidase	Cell wall misc	Fungal multicellularity	0.0000000	0.0000002	-1.017996	0.1840805	6.2919447	0.4902103	0.0021095	0.2362584	0.0751861	0.2362584	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503NZ6V	GO_function: GO:0004601 - peroxidase activity [Evidence IEA]	IPR000028 Chloroperoxidase, IPR036851 Chloroperoxidase-like superfamily	PF01328	NA	SignalP(1-18,cutsite=VTA-FP,prob=0.7778)
XANPAGTX0501_001458-T1	IPR002889	IPR	Carbohydrate-binding WSC	Cell wall remodeling	Fungal multicellularity	0.0000000	0.0000000	-2.475919	0.2332706	9.6373325	1.9092048	0.0001288	0.3826537	0.1020698	0.3826537	lichen	hypothetical protein	NA	G:(G) Carbohydrate transport and metabolism, O:(O) Posttranslational modification, protein turnover, chaperones, S:(S) Function unknown	ENOG503NVEA, ENOG503P073	NA	IPR002889 Carbohydrate-binding WSC, IPR018535 Domain of unknown function DUF1996	PF01822, PF09362	NA	SignalP(1-23,cutsite=VSA-QR,prob=0.7711)
XANPAGTX0501_001856-T1	IPR037176	IPR	Osmotin/thaumatin-like superfamily	Cell wall remodeling	Fungal multicellularity	0.0000000	0.0000000	-3.823871	0.4267541	5.3759413	4.9088637	0.0242365	1.2568772	0.1485279	1.2568772	lichen	hypothetical protein	NA	NA	ENOG503P50I	NA	IPR037176 Osmotin/thaumatin-like superfamily	NA	NA	SignalP(1-19,cutsite=VWA-RG,prob=0.6259), SignalP(1-22,cutsite=CSA-QR,prob=0.7214), SignalP(1-24,cutsite=TRA-TS,prob=0.4684)
XANPAGTX0501_010026-T1	IPR036779	IPR	LysM domain superfamily	Cell wall remodeling	Fungal multicellularity	0.0000001	0.0000004	-1.349396	0.2502038	4.0870332	0.6235125	0.0272033	0.1449998	0.4131691	0.4131691	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503P0BZ	NA	IPR018392 LysM domain, IPR036779 LysM domain superfamily	PF01476	NA	SignalP(1-27,cutsite=ALA-QG,prob=0.6344), SignalP(1-27,cutsite=TYA-QD,prob=0.9903)
XANPAGTX0501_000318-T1	GH55	CAZy	beta-1,3-glucanase	Cell wall remodeling	Fungal multicellularity	0.0000000	0.0000000	-1.300846	0.0856469	7.1347358	0.4748922	0.0009102	0.0506905	0.0441826	0.0506905	lichen	hypothetical protein	GH55	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NW2N	NA	IPR011050 Pectin lyase fold/virulence factor, IPR012334 Pectin lyase fold, IPR024535 Pectate lyase superfamily protein	PF12708	NA	NA
XANPAGTX0501_000758-T1	GH16	CAZy	act on beta-1,4 or beta-1,3 glycosidic bonds in glucans and galactans	Cell wall remodeling	Fungal multicellularity	0.0000000	0.0000000	-1.982662	0.1791060	9.2111023	1.2051783	0.0001580	0.2255009	0.0782054	0.2255009	lichen	hypothetical protein	GH16	G:(G) Carbohydrate transport and metabolism	ENOG503NW22	GO_function: GO:0004553 - hydrolase activity, hydrolyzing O-glycosyl compounds [Evidence IEA], GO_process: GO:0005975 - carbohydrate metabolic process [Evidence IEA]	IPR000757 Glycoside hydrolase family 16, IPR013320 Concanavalin A-like lectin/glucanase domain superfamily	PF00722	NA	NA	K20697
XANPAGTX0501_007404-T1	GH18	CAZy	chitinases	Cell wall remodeling	Fungal multicellularity	0.0000000	0.0000002	-1.446909	0.2615680	3.9484201	0.8108561	0.0276383	0.2678044	0.4536455	0.4536455	lichen	hypothetical protein	GH18	G:(G) Carbohydrate transport and metabolism	ENOG503NWIT	GO_function: GO:0008061 - chitin binding [Evidence IEA], GO_process: GO:0005975 - carbohydrate metabolic process [Evidence IEA]	IPR001002 Chitin-binding, type 1, IPR001223 Glycoside hydrolase family 18, catalytic domain, IPR011583 Chitinase II, IPR017853 Glycoside hydrolase superfamily, IPR036861 Endochitinase-like superfamily	PF00187, PF00704	NA	SignalP(1-25,cutsite=SDA-SI,prob=0.8587)
XANPAGTX0501_009511-T1	GH16	CAZy	act on beta-1,4 or beta-1,3 glycosidic bonds in glucans and galactans	Cell wall remodeling	Fungal multicellularity	0.0000000	0.0000000	-1.745629	0.2996914	6.3367513	1.3747949	0.0030164	0.6287850	0.0726285	0.6287850	lichen	hypothetical protein	GH16	G:(G) Carbohydrate transport and metabolism, O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NZM7, ENOG503PDKW	GO_function: GO:0004553 - hydrolase activity, hydrolyzing O-glycosyl compounds [Evidence IEA], GO_function: GO:0008061 - chitin binding [Evidence IEA], GO_process: GO:0005975 - carbohydrate metabolic process [Evidence IEA]	IPR000757 Glycoside hydrolase family 16, IPR001002 Chitin-binding, type 1, IPR008264 Beta-glucanase, IPR013320 Concanavalin A-like lectin/glucanase domain superfamily, IPR036861 Endochitinase-like superfamily	PF00722	NA	SignalP(1-22,cutsite=VSA-AC,prob=0.8043), SignalP(1-22,cutsite=VSA-AC,prob=0.8317), SignalP(1-25,cutsite=AWA-DC,prob=0.9518), SignalP(1-26,cutsite=VLG-KC,prob=0.6494)	K01216
XANPAGTX0501_009699-T1	GH16	CAZy	act on beta-1,4 or beta-1,3 glycosidic bonds in glucans and galactans	Cell wall remodeling	Fungal multicellularity	0.0000000	0.0000000	-1.923092	0.1546199	7.0826922	1.0912947	0.0013485	0.1668271	0.0450414	0.1668271	lichen	hypothetical protein	GH16	G:(G) Carbohydrate transport and metabolism, O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NZM7, ENOG503PDKW	GO_function: GO:0004553 - hydrolase activity, hydrolyzing O-glycosyl compounds [Evidence IEA], GO_function: GO:0008061 - chitin binding [Evidence IEA], GO_process: GO:0005975 - carbohydrate metabolic process [Evidence IEA]	IPR000757 Glycoside hydrolase family 16, IPR001002 Chitin-binding, type 1, IPR008264 Beta-glucanase, IPR013320 Concanavalin A-like lectin/glucanase domain superfamily, IPR036861 Endochitinase-like superfamily	PF00722	NA	SignalP(1-22,cutsite=VSA-AC,prob=0.8043), SignalP(1-22,cutsite=VSA-AC,prob=0.8317), SignalP(1-25,cutsite=AWA-DC,prob=0.9518), SignalP(1-26,cutsite=VLG-KC,prob=0.6494)
XANPAGTX0501_009731-T1	GH71	CAZy	Endo-_-1,3-glucanase	Cell wall remodeling	Fungal multicellularity	0.0000000	0.0000000	-1.215351	0.1510826	7.2847225	0.5259227	0.0008601	0.1597087	0.0422406	0.1597087	lichen	hypothetical protein	GH71	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NVTC	GO_function: GO:0016787 - hydrolase activity [Evidence IEA]	IPR005197 Glycoside hydrolase family 71	PF03659	NA	SignalP(1-22,cutsite=AST-RK,prob=0.4524)	K08254
XANPAGTX0501_010366-T1	AA9	CAZy	Lytic polysaccharide monooxygenase	Cell wall remodeling	Fungal multicellularity	0.0000000	0.0000000	-1.609971	0.2095510	6.8304354	0.9490572	0.0015725	0.3073230	0.0513842	0.3073230	lichen	hypothetical protein	AA9	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NYCR, ENOG503Q4YD	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA], GO_function: GO:0008061 - chitin binding [Evidence IEA]	IPR001002 Chitin-binding, type 1, IPR005103 Auxiliary Activity family 9, IPR013087 Zinc finger C2H2-type, IPR018371 Chitin-binding, type 1, conserved site, IPR036861 Endochitinase-like superfamily	PF00187, PF03443	NA	SignalP(1-21,cutsite=ASA-HT,prob=0.7581), SignalP(1-21,cutsite=VSA-HG,prob=0.4970)
XANPAGTX0501_000685-T1	IPR021765	IPR	Mycotoxin biosynthesis protein UstYa-like	Defense	Fungal multicellularity	0.0000000	0.0000000	-1.440362	0.1865376	5.9687789	0.7572478	0.0032712	0.2415027	0.0950875	0.2415027	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503P6KY	GO_process: GO:0043386 - mycotoxin biosynthetic process [Evidence IEA]	IPR021765 Mycotoxin biosynthesis protein UstYa-like	PF11807	NA	NA
XANPAGTX0501_001064-T1	IPR021765	IPR	Mycotoxin biosynthesis protein UstYa-like	Defense	Fungal multicellularity	0.0000000	0.0000000	-1.531610	0.2503122	6.7472404	1.0143587	0.0016671	0.4390870	0.0542905	0.4390870	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503NZ4Z, ENOG503P5F9	GO_process: GO:0043386 - mycotoxin biosynthetic process [Evidence IEA]	IPR021765 Mycotoxin biosynthesis protein UstYa-like	PF11807	NA	NA
XANPAGTX0501_009135-T1	IPR015131	IPR	Killer toxin, Kp4	Defense	Fungal multicellularity	0.0000000	0.0000000	-4.527295	0.2528839	4.2871611	5.5831327	0.0833572	0.3664998	0.3579512	0.3664998	lichen	hypothetical protein	NA	NA	NA	GO_component: GO:0005576 - extracellular region [Evidence IEA], GO_process: GO:0009405 - pathogenesis [Evidence IEA]	IPR011329 Killer toxin Kp4/SMK, IPR015131 Killer toxin, Kp4	PF09044	NA	SignalP(1-19,cutsite=ALA-LV,prob=0.6255)
XANPAGTX0501_005629-T1	IPR030395	IPR	Glycerophosphodiester phosphodiesterase domain	Lipid metabolism	Fungal multicellularity	0.0001504	0.0005043	-1.163876	0.3070604	6.7099464	0.9798861	0.0016349	0.6616189	0.0556450	0.6616189	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503NY4Y	GO_function: GO:0008081 - phosphoric diester hydrolase activity [Evidence IEA], GO_process: GO:0006629 - lipid metabolic process [Evidence IEA]	IPR017946 PLC-like phosphodiesterase, TIM beta/alpha-barrel domain superfamily, IPR030395 Glycerophosphodiester phosphodiesterase domain	PF03009	NA	SignalP(1-18,cutsite=AVA-IP,prob=0.6848)
XANPAGTX0501_006790-T1	IPR005804	IPR	Fatty acid desaturase domain	Lipid metabolism	Fungal multicellularity	0.0000000	0.0000000	-1.449602	0.1594914	7.8840801	0.7004734	0.0005100	0.1784297	0.0436319	0.1784297	lichen	Oleate hydroxylase fah12	NA	I:(I) Lipid transport and metabolism	ENOG503NUUZ	GO_process: GO:0006629 - lipid metabolic process [Evidence IEA]	IPR005804 Fatty acid desaturase domain	PF00487	NA	NA	K10256
XANPAGTX0501_008061-T1	IPR002225	IPR	3-beta hydroxysteroid dehydrogenase/isomerase	Lipid metabolism	Fungal multicellularity	0.0000000	0.0000000	-4.544181	0.7741697	1.9706831	9.2532912	0.0286329	4.1874052	1.1364158	4.1874052	lichen	hypothetical protein	NA	E:(E) Amino acid transport and metabolism, G:(G) Carbohydrate transport and metabolism, I:(I) Lipid transport and metabolism, M:(M) Cell wall/membrane/envelope biogenesis	ENOG503NWMM, ENOG50KOG1430	GO_function: GO:0003854 - 3-beta-hydroxy-delta5-steroid dehydrogenase activity [Evidence IEA], GO_function: GO:0016616 - oxidoreductase activity, acting on the CH-OH group of donors, NAD or NADP as acceptor [Evidence IEA], GO_process: GO:0006694 - steroid biosynthetic process [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR002225 3-beta hydroxysteroid dehydrogenase/isomerase, IPR036291 NAD(P)-binding domain superfamily	PF01073, PF01370, PF04321, PF07993, PF08659, PF16363	NA	NA
XANPAGTX0501_002599-T1	IPR001810	IPR	F-box domain	Protein ubiquitination	Fungal multicellularity	0.0000000	0.0000000	-2.103673	0.1625696	5.5942933	1.2910842	0.0062258	0.1796877	0.1254083	0.1796877	lichen	hypothetical protein	NA	NA	ENOG503P83U	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR001810 F-box domain, IPR032675 Leucine-rich repeat domain superfamily	NA	NA	NA
XANPAGTX0501_002780-T1	IPR000210	IPR	BTB/POZ domain	Protein ubiquitination	Fungal multicellularity	0.0000000	0.0000000	-4.725996	0.2765667	5.3668729	6.1301110	0.0257584	0.5123031	0.1496018	0.5123031	lichen	hypothetical protein	NA	NA	NA	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR000210 BTB/POZ domain, IPR011333 SKP1/BTB/POZ domain superfamily	NA	NA	NA
XANPAGTX0501_002947-T1	IPR017907	IPR	Zinc finger; RING-type; conserved site	Protein ubiquitination	Fungal multicellularity	0.0000000	0.0000000	-1.534891	0.2355584	6.0934408	0.9682616	0.0032977	0.3870300	0.0869775	0.3870300	lichen	hypothetical protein	NA	NA	NA	GO_function: GO:0005524 - ATP binding [Evidence IEA], GO_function: GO:0046872 - metal ion binding [Evidence IEA]	IPR000330 SNF2, N-terminal, IPR001650 Helicase, C-terminal, IPR001841 Zinc finger, RING-type, IPR013083 Zinc finger, RING/FYVE/PHD-type, IPR014001 Helicase superfamily 1/2, ATP-binding domain, IPR017907 Zinc finger, RING-type, conserved site, IPR018957 Zinc finger, C3HC4 RING-type, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR038718 SNF2-like, N-terminal domain superfamily	PF00097, PF00176, PF00271	NA	NA
XANPAGTX0501_003212-T1	IPR001810	IPR	F-box domain	Protein ubiquitination	Fungal multicellularity	0.0000000	0.0000000	-3.203922	0.3662345	2.9421745	3.4887428	0.1003648	0.8431542	0.7899210	0.8431542	lichen	hypothetical protein	NA	NA	NA	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR001810 F-box domain, IPR032675 Leucine-rich repeat domain superfamily, IPR036047 F-box-like domain superfamily	NA	NA	NA
XANPAGTX0501_003213-T1	IPR001810	IPR	F-box domain	Protein ubiquitination	Fungal multicellularity	0.0000000	0.0000000	-2.706735	0.4278400	2.0193513	3.0773266	0.1678265	1.1146774	1.1198147	1.1198147	lichen	hypothetical protein	NA	NA	NA	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR001810 F-box domain, IPR032675 Leucine-rich repeat domain superfamily, IPR036047 F-box-like domain superfamily	NA	NA	NA
XANPAGTX0501_003645-T1	IPR000210	IPR	BTB/POZ domain	Protein ubiquitination	Fungal multicellularity	0.0000000	0.0000000	-1.083223	0.0927463	6.6170746	0.3401060	0.0014582	0.0455384	0.0590515	0.0590515	lichen	hypothetical protein	NA	NA	ENOG503PF7V	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR000210 BTB/POZ domain, IPR011333 SKP1/BTB/POZ domain superfamily	PF00651	NA	NA
XANPAGTX0501_005550-T1	IPR001810	IPR	F-box domain	Protein ubiquitination	Fungal multicellularity	0.0000034	0.0000164	-1.039899	0.2239938	6.9236618	0.6120166	0.0011770	0.3517658	0.0485056	0.3517658	lichen	hypothetical protein	NA	NA	NA	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR001810 F-box domain, IPR036047 F-box-like domain superfamily	PF00646, PF12937	NA	NA
XANPAGTX0501_006203-T1	IPR017907	IPR	Zinc finger; RING-type; conserved site	Protein ubiquitination	Fungal multicellularity	0.0000000	0.0000000	-2.316940	0.3110455	3.4826578	1.9648390	0.0790759	0.5599209	0.6015053	0.6015053	lichen	hypothetical protein	NA	O:(O) Posttranslational modification, protein turnover, chaperones, S:(S) Function unknown	ENOG503NVJG, ENOG50KOG1812	NA	IPR001841 Zinc finger, RING-type, IPR002867 IBR domain, IPR013083 Zinc finger, RING/FYVE/PHD-type, IPR017907 Zinc finger, RING-type, conserved site	PF01485	NA	NA
XANPAGTX0501_007869-T1	IPR000210	IPR	BTB/POZ domain	Protein ubiquitination	Fungal multicellularity	0.0000000	0.0000000	-3.026743	0.4066037	4.1506594	3.4230277	0.0485304	1.1144566	0.3951948	1.1144566	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503P2K5, ENOG503P7DP, ENOG503Q0BF	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR000210 BTB/POZ domain, IPR011333 SKP1/BTB/POZ domain superfamily	PF00651	NA	NA
XANPAGTX0501_008855-T1	IPR000210	IPR	BTB/POZ domain	Protein ubiquitination	Fungal multicellularity	0.0000000	0.0000000	-1.523515	0.2452835	4.1953774	0.9912406	0.0228782	0.4003443	0.3827872	0.4003443	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503NWB1, ENOG503P1ID, ENOG503P294, ENOG503P8DT, ENOG503P901	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR000210 BTB/POZ domain, IPR011333 SKP1/BTB/POZ domain superfamily	PF00651	NA	NA
XANPAGTX0501_008856-T1	IPR001810	IPR	F-box domain	Protein ubiquitination	Fungal multicellularity	0.0000000	0.0000000	-4.856873	0.3936334	2.1539856	6.4879093	0.0168138	0.5655380	1.0731598	1.0731598	lichen	hypothetical protein	NA	NA	ENOG503P83U	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR001810 F-box domain, IPR032675 Leucine-rich repeat domain superfamily	NA	NA	NA
XANPAGTX0501_009316-T1	IPR001810	IPR	F-box domain	Protein ubiquitination	Fungal multicellularity	0.0001248	0.0004263	-1.327815	0.3461089	5.2202197	1.2555191	0.0096639	0.8330062	0.1684250	0.8330062	lichen	hypothetical protein	NA	NA	ENOG503PEPR	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR001810 F-box domain, IPR036047 F-box-like domain superfamily	PF00646	NA	NA
XANPAGTX0501_009461-T1	IPR001810	IPR	F-box domain	Protein ubiquitination	Fungal multicellularity	0.0000000	0.0000000	-1.311848	0.1832877	5.9012434	0.6602350	0.0059265	0.2303926	0.0998476	0.2303926	lichen	hypothetical protein	NA	NA	NA	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR001810 F-box domain, IPR036047 F-box-like domain superfamily	NA	NA	NA
XANPAGTX0501_009738-T1	IPR001810	IPR	F-box domain	Protein ubiquitination	Fungal multicellularity	0.0000000	0.0000000	-4.066189	0.3909471	2.3572608	4.6616832	0.0740251	0.4526320	1.0011227	1.0011227	lichen	hypothetical protein	NA	NA	NA	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR001810 F-box domain, IPR032675 Leucine-rich repeat domain superfamily, IPR036047 F-box-like domain superfamily	NA	NA	NA
XANPAGTX0501_010478-T1	IPR000589	IPR	Ribosomal protein S15	Ribosomal genes	Fungal multicellularity	0.0195798	0.0385384	-1.973841	0.8455801	0.4639321	5.8288741	0.4185652	4.6111305	1.5179814	4.6111305	lichen	hypothetical protein	NA	J:(J) Translation, ribosomal structure and biogenesis	ENOG503P03T	GO_component: GO:0005840 - ribosome [Evidence IEA], GO_function: GO:0003735 - structural constituent of ribosome [Evidence IEA], GO_process: GO:0006412 - translation [Evidence IEA]	IPR000589 Ribosomal protein S15, IPR009068 S15/NS1, RNA-binding	PF00312	NA	NA
XANPAGTX0501_002643-T1	IPR019479	IPR	Peroxiredoxin, C-terminal	Stress response genes	Fungal multicellularity	0.0000051	0.0000233	-1.089788	0.2388511	8.4324664	0.6853556	0.0002918	0.4010245	0.0527390	0.4010245	lichen	peroxiredoxin 1	NA	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NW6E	GO_function: GO:0016209 - antioxidant activity [Evidence IEA], GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_function: GO:0051920 - peroxiredoxin activity [Evidence IEA], GO_process: GO:0045454 - cell redox homeostasis [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR000866 Alkyl hydroperoxide reductase subunit C/ Thiol specific antioxidant, IPR013766 Thioredoxin domain, IPR019479 Peroxiredoxin, C-terminal, IPR024706 Peroxiredoxin, AhpC-type, IPR036249 Thioredoxin-like superfamily	PF00578, PF08534, PF10417	NA	NA	K11188
XANPAGTX0501_000142-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-1.141449	0.1582778	6.8827690	0.4972641	0.0012527	0.1749742	0.0497048	0.1749742	lichen	hypothetical protein	NA	U:(U) Intracellular trafficking, secretion, and vesicular transport	ENOG503PBXT	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR036259 MFS transporter superfamily	NA	NA	NA
XANPAGTX0501_000684-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-1.109947	0.1888421	6.5257143	0.5514127	0.0020085	0.2488507	0.0629072	0.2488507	lichen	hypothetical protein	NA	J:(J) Translation, ribosomal structure and biogenesis, S:(S) Function unknown	ENOG503P3D5, ENOG503P53R, ENOG503P672, ENOG503PACP, ENOG503PAGX, ENOG503PEB6, ENOG503PEZW, ENOG503PU88	NA	IPR036259 MFS transporter superfamily	NA	NA	NA
XANPAGTX0501_000704-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-1.574832	0.1749756	8.3347504	0.8307574	0.0003359	0.2150351	0.0506946	0.2150351	lichen	hypothetical protein	NA	G:(G) Carbohydrate transport and metabolism	ENOG503NWTF	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_001448-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-2.050145	0.1423924	7.5074016	1.1934838	0.0009080	0.1417203	0.0412267	0.1417203	lichen	hypothetical protein	NA	G:(G) Carbohydrate transport and metabolism	ENOG503NWXD	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_001653-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-2.040820	0.2796368	7.2710543	1.5767940	0.0011777	0.5488961	0.0423795	0.5488961	lichen	hypothetical protein	NA	U:(U) Intracellular trafficking, secretion, and vesicular transport	ENOG503NVYI	GO_component: GO:0016020 - membrane [Evidence IEA], GO_component: GO:0016021 - integral component of membrane [Evidence IEA], GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF00083	NA	NA
XANPAGTX0501_002486-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-1.412661	0.1265086	8.8506190	0.6099226	0.0001842	0.1123987	0.0641021	0.1123987	lichen	hypothetical protein	NA	U:(U) Intracellular trafficking, secretion, and vesicular transport	ENOG5039JDB	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA	K14636
XANPAGTX0501_003337-T2	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-2.034775	0.1458708	7.9940814	1.1845128	0.0016016	0.1480803	0.0450310	0.1480803	lichen	acid phosphatase pho5	NA	P:(P) Inorganic ion transport and metabolism	ENOG503NTWV	GO_component: GO:0016021 - integral component of membrane [Evidence IEA], GO_function: GO:0005315 - inorganic phosphate transmembrane transporter activity [Evidence IEA], GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0006817 - phosphate ion transport [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR004738 Phosphate permease, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF00083, PF07690	NA	NA	K08176
XANPAGTX0501_004383-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-1.077558	0.1382020	6.1155704	0.4212716	0.0026516	0.1317055	0.0856224	0.1317055	lichen	hypothetical protein	NA	U:(U) Intracellular trafficking, secretion, and vesicular transport	ENOG503NZ12	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_004624-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-1.314078	0.1771810	8.3744046	0.6467740	0.0003043	0.2205301	0.0514996	0.2205301	lichen	hypothetical protein	NA	P:(P) Inorganic ion transport and metabolism	ENOG503NWEV	GO_component: GO:0016021 - integral component of membrane [Evidence IEA], GO_function: GO:0015112 - nitrate transmembrane transporter activity [Evidence IEA], GO_function: GO:0015113 - nitrite transmembrane transporter activity [Evidence IEA], GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0015706 - nitrate transport [Evidence IEA], GO_process: GO:0015707 - nitrite transport [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR004737 Nitrate transporter NarK/NarU-like, IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA	K02575
XANPAGTX0501_005489-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-1.163031	0.1921648	5.0564185	0.5903133	0.0084712	0.2512935	0.1928335	0.2512935	lichen	hypothetical protein	NA	J:(J) Translation, ribosomal structure and biogenesis, S:(S) Function unknown	ENOG503P3D5, ENOG503P53R, ENOG503P672, ENOG503PACP, ENOG503PAGX, ENOG503PEB6, ENOG503PEZW, ENOG503PU88	NA	IPR036259 MFS transporter superfamily	NA	NA	NA
XANPAGTX0501_005571-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000162	0.0000670	-1.979783	0.4592104	8.3631070	2.4151252	0.0005081	1.4828831	0.0512669	1.4828831	lichen	hypothetical protein	NA	U:(U) Intracellular trafficking, secretion, and vesicular transport	ENOG503NVYI	GO_component: GO:0016020 - membrane [Evidence IEA], GO_component: GO:0016021 - integral component of membrane [Evidence IEA], GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF00083, PF07690	NA	NA
XANPAGTX0501_005572-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000042	0.0000199	-1.902547	0.4136627	8.0750795	2.0701080	0.0006166	1.2031020	0.0461878	1.2031020	lichen	hypothetical protein	NA	C:(C) Energy production and conversion	ENOG503NVYI	GO_component: GO:0016021 - integral component of membrane [Evidence IEA], GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR005828 Major facilitator, sugar transporter-like, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF00083, PF07690	NA	NA
XANPAGTX0501_005708-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000913	0.0003229	-1.185932	0.3031025	7.3466698	0.9765257	0.0010962	0.6451695	0.0417223	0.6451695	lichen	hypothetical protein	NA	NA	NA	NA	IPR036259 MFS transporter superfamily	NA	NA	NA
XANPAGTX0501_006293-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-1.523619	0.1515478	5.8157216	0.7390019	0.0019412	0.1596180	0.1062851	0.1596180	lichen	hypothetical protein	NA	U:(U) Intracellular trafficking, secretion, and vesicular transport	ENOG503NY2M	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR001958 Tetracycline resistance protein TetA/multidrug resistance protein MdtG, IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_006367-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-1.165988	0.1779372	6.0716021	0.5563255	0.0397024	0.1830209	0.0883388	0.1830209	lichen	hypothetical protein	NA	U:(U) Intracellular trafficking, secretion, and vesicular transport	ENOG503P192	GO_component: GO:0016021 - integral component of membrane [Evidence IEA], GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR005829 Sugar transporter, conserved site, IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF06609, PF07690	NA	NA
XANPAGTX0501_007882-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000003	0.0000018	-1.118012	0.2186339	7.5045937	0.6382714	0.0007728	0.3354809	0.0412268	0.3354809	lichen	hypothetical protein	NA	P:(P) Inorganic ion transport and metabolism	ENOG503NV25, ENOG503NVXD	GO_component: GO:0016020 - membrane [Evidence IEA], GO_component: GO:0016021 - integral component of membrane [Evidence IEA], GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF00083, PF07690	NA	NA
XANPAGTX0501_007969-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-4.953328	0.5069936	2.9557249	7.9076654	0.0393170	1.7688444	0.7850587	1.7688444	lichen	hypothetical protein	NA	U:(U) Intracellular trafficking, secretion, and vesicular transport	ENOG503NY2N	GO_component: GO:0016020 - membrane [Evidence IEA], GO_component: GO:0016021 - integral component of membrane [Evidence IEA], GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF00083, PF07690	NA	NA
XANPAGTX0501_009192-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0005189	0.0015466	-2.757741	0.7945560	0.9234596	6.1930470	0.0084817	4.4325227	1.4367431	4.4325227	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503NZPM, ENOG503P0C6	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_009193-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0127386	0.0264910	-1.140842	0.4579864	3.9698522	1.7497802	0.0594367	1.4160567	0.4472717	1.4160567	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503NZPM, ENOG503P0C6	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_009202-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0172004	0.0344039	-1.037746	0.4355895	4.2743864	1.5575975	0.0853149	1.2493951	0.3613539	1.2493951	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503NZPM, ENOG503P0C6	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_009320-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-1.039645	0.1772711	4.9389021	0.4022133	0.0084114	0.1270947	0.2126476	0.2126476	lichen	hypothetical protein	NA	U:(U) Intracellular trafficking, secretion, and vesicular transport	ENOG503NW0J	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF06609, PF07690	NA	NA
XANPAGTX0501_009472-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000001	0.0000004	-1.295828	0.2396961	6.8787995	0.8115872	0.0013620	0.4027987	0.0498269	0.4027987	lichen	microtubule integrity protein mal3	AA8	D:(D) Cell cycle control, cell division, chromosome partitioning, Z:(Z) Cytoskeleton	ENOG503NZ7G	NA	IPR005018 DOMON domain, IPR006593 Cytochrome b561/ferric reductase transmembrane, IPR015920 Cellobiose dehydrogenase, cytochrome domain, IPR018825 Domain of unknown function DUF2427, IPR036259 MFS transporter superfamily, IPR038697 None	PF03188, PF10348, PF16010	NA	SignalP(1-24,cutsite=VAA-LG,prob=0.4180)
XANPAGTX0501_009914-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0001809	0.0005945	-1.018839	0.2721027	5.9481642	0.7630175	0.0038100	0.5170222	0.0965117	0.5170222	lichen	hypothetical protein	NA	J:(J) Translation, ribosomal structure and biogenesis, S:(S) Function unknown	ENOG503P3D5, ENOG503P53R, ENOG503P672, ENOG503PACP, ENOG503PAGX, ENOG503PEB6, ENOG503PEZW, ENOG503PU88	NA	IPR036259 MFS transporter superfamily	NA	NA	NA
XANPAGTX0501_010175-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-2.074202	0.1847304	4.8658520	1.2826447	0.0140951	0.1951451	0.2259589	0.2259589	lichen	hypothetical protein	NA	G:(G) Carbohydrate transport and metabolism	ENOG503NWTF	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_010196-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-1.250151	0.1772507	7.4224366	0.6057591	0.0007385	0.2202696	0.0413557	0.2202696	lichen	High-affinity nicotinic acid transporter	NA	G:(G) Carbohydrate transport and metabolism	ENOG503NU7U	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_010444-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	-1.523619	0.1515478	5.8157216	0.7390019	0.0019412	0.1596180	0.1062851	0.1596180	lichen	hypothetical protein	NA	U:(U) Intracellular trafficking, secretion, and vesicular transport	ENOG503NY2M	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR001958 Tetracycline resistance protein TetA/multidrug resistance protein MdtG, IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_010683-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0078090	0.0171585	-1.253016	0.4710201	2.2412448	1.8993774	0.1083009	1.4523687	1.0424352	1.4523687	lichen	hypothetical protein	NA	G:(G) Carbohydrate transport and metabolism	ENOG503NWXD, ENOG503NYSR, ENOG503P0M5	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_001470-T1	IPR017981	IPR	GPCR, family 2-like, transmembrane domain	G-proteins and GPCR	Signal transduction	0.0000000	0.0000000	-2.170778	0.0967251	8.1920251	1.2473355	0.0004888	0.0653240	0.0480601	0.0653240	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503NZXQ, ENOG503PC36, ENOG503Q4SW	GO_component: GO:0016021 - integral component of membrane [Evidence IEA], GO_function: GO:0004888 - transmembrane signaling receptor activity [Evidence IEA], GO_process: GO:0007166 - cell surface receptor signaling pathway [Evidence IEA]	IPR017981 GPCR, family 2-like, transmembrane domain, IPR023041 Glucose receptor Git3, N-terminal	PF00002, PF05462, PF11710	NA	NA	K22987
XANPAGTX0501_007151-T1	K19806	KEGG	PTP2_3; tyrosine-protein phosphatase 2/3 [EC:3.1.3.48]	MAPK signaling pathway	Signal transduction	0.0000000	0.0000000	-1.044999	0.1589452	7.2114036	0.4457196	0.0008186	0.1768975	0.0430799	0.1768975	lichen	phosphotyrosine-specific ptp2-like protein	NA	T:(T) Signal transduction mechanisms	ENOG503NW1A	GO_function: GO:0004725 - protein tyrosine phosphatase activity [Evidence IEA], GO_function: GO:0016791 - phosphatase activity [Evidence IEA], GO_process: GO:0006470 - protein dephosphorylation [Evidence IEA], GO_process: GO:0016311 - dephosphorylation [Evidence IEA]	IPR000242 Tyrosine-specific protein phosphatase, PTPase domain, IPR000387 Tyrosine-specific protein phosphatases domain, IPR001763 Rhodanese-like domain, IPR003595 Protein-tyrosine phosphatase, catalytic, IPR016130 Protein-tyrosine phosphatase, active site, IPR029021 Protein-tyrosine phosphatase-like, IPR036873 Rhodanese-like domain superfamily	PF00581	NA	NA	K19806
XANPAGTX0501_001453-T1	IPR034812	IPR	Psi-factor producing oxygenase-like, N-terminal heme peroxidase domain	Oxylipins	Signal transduction	0.0000000	0.0000000	-1.765282	0.2482255	8.4889113	1.2008493	0.0003173	0.4331187	0.0540158	0.4331187	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503NWZ7	GO_function: GO:0004601 - peroxidase activity [Evidence IEA], GO_function: GO:0005506 - iron ion binding [Evidence IEA], GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_function: GO:0016705 - oxidoreductase activity, acting on paired donors, with incorporation or reduction of molecular oxygen [Evidence IEA], GO_function: GO:0020037 - heme binding [Evidence IEA], GO_process: GO:0006979 - response to oxidative stress [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR010255 Haem peroxidase superfamily, IPR019791 Haem peroxidase, animal-type, IPR034812 Psi-factor producing oxygenase, N-terminal heme peroxidase domain, IPR036396 Cytochrome P450 superfamily, IPR037120 Haem peroxidase domain superfamily, animal type	NA	NA	NA	K11987
XANPAGTX0501_006918-T1	IPR034812	IPR	Psi-factor producing oxygenase-like, N-terminal heme peroxidase domain	Oxylipins	Signal transduction	0.0000000	0.0000000	-4.100913	0.1845404	8.1885430	4.4560873	0.0012045	0.2383560	0.0480008	0.2383560	lichen	hypothetical protein	NA	S:(S) Function unknown	ENOG503NWZ7	GO_function: GO:0004601 - peroxidase activity [Evidence IEA], GO_function: GO:0005506 - iron ion binding [Evidence IEA], GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_function: GO:0016705 - oxidoreductase activity, acting on paired donors, with incorporation or reduction of molecular oxygen [Evidence IEA], GO_function: GO:0020037 - heme binding [Evidence IEA], GO_process: GO:0006979 - response to oxidative stress [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR010255 Haem peroxidase superfamily, IPR017972 Cytochrome P450, conserved site, IPR019791 Haem peroxidase, animal-type, IPR034812 Psi-factor producing oxygenase, N-terminal heme peroxidase domain, IPR036396 Cytochrome P450 superfamily	NA	NA	NA	K11987
XANPAGTX0501_006802-T1	IPR037525	IPR	Velvet domain	Velvet	Signal transduction	0.0000000	0.0000001	-1.100956	0.1966999	6.1839450	0.5669688	0.0025878	0.2695823	0.0815457	0.2695823	lichen	hypothetical protein	NA	NA	NA	NA	IPR037525 Velvet domain, IPR038491 Velvet domain superfamily	NA	NA	NA
XANPAGTX0501_010363-T1	IPR037525	IPR	Velvet domain	Velvet	Signal transduction	0.0000000	0.0000000	-1.464176	0.1453582	8.4790321	0.6819161	0.0002791	0.1483525	0.0537871	0.1483525	lichen	hypothetical protein	NA	K:(K) Transcription	ENOG503NZB3	NA	IPR037525 Velvet domain, IPR038491 Velvet domain superfamily	NA	NA	NA

• In the culture-upregulated genes, the percentage is even higher: 10.6382979%

mult_gene_table_culture<-mult_gene_table %>% left_join(sig, by = c("TranscriptID"="target_id")) %>%
  filter(change=="culture") %>% arrange(Function) %>% arrange(Function_type) %>% left_join(funannot %>% select(TranscriptID,Product,CAZyme_new,COG_new,EggNog_new,GO.Terms_new,InterPro_new,PFAM_new,Protease_new,Secreted_new,KO))
mult_gene_table_culture %>% 
  kable(format = "html", col.names = colnames(mult_gene_table_culture)) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

TranscriptID	ID	Annotation_type	Description	Function	Function_type	pval	qval	b	se_b	mean_obs	var_obs	tech_var	sigma_sq	smooth_sigma_sq	final_sigma_sq	change	Product	CAZyme_new	COG_new	EggNog_new	GO.Terms_new	InterPro_new	PFAM_new	Protease_new	Secreted_new	KO
XANPAGTX0501_004804-T1	IPR000504	IPR	RNA recognition motif domain	RNA binding proteins	Expression regulation	0.0036598	0.0088276	2.478043	0.8527084	2.5655048	6.4749178	1.1349997	3.9798549	0.9260916	3.9798549	culture	hypothetical protein	NA	A:(A) RNA processing and modification	ENOG503NV9Q	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA]	IPR000504 RNA recognition motif domain, IPR012677 Nucleotide-binding alpha-beta plait domain superfamily, IPR034215 RBM42, RNA recognition motif, IPR035979 RNA-binding domain superfamily	PF00076	NA	NA	K25079
XANPAGTX0501_005358-T1	IPR000504	IPR	RNA recognition motif domain	RNA binding proteins	Expression regulation	0.0000000	0.0000000	1.002459	0.0776394	7.6977167	0.2783380	0.0005501	0.0262776	0.0418529	0.0418529	culture	Peptidyl-prolyl cis-trans isomerase pin4	NA	A:(A) RNA processing and modification	ENOG503NZ7N	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA]	IPR000504 RNA recognition motif domain, IPR001374 R3H domain, IPR012677 Nucleotide-binding alpha-beta plait domain superfamily, IPR034186 Pin4-like, RNA recognition motif, IPR035979 RNA-binding domain superfamily, IPR036867 R3H domain superfamily	PF00076, PF01424	NA	NA
XANPAGTX0501_001980-T1	IPR036864	IPR	Zn(2)-C6 fungal-type DNA-binding domain superfamily	Transcription factors	Expression regulation	0.0000000	0.0000001	1.496530	0.2588154	8.9558330	1.0170378	0.0002066	0.4710013	0.0677463	0.4710013	culture	hypothetical protein	NA	S:(S) Function unknown	ENOG503NVDH	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00172	NA	NA
XANPAGTX0501_002161-T1	IPR036864	IPR	Zn(2)-C6 fungal-type DNA-binding domain superfamily	Transcription factors	Expression regulation	0.0000000	0.0000000	2.266902	0.3445925	5.5436653	2.0965103	0.0073826	0.8279199	0.1303501	0.8279199	culture	hypothetical protein	NA	NA	NA	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	NA	NA	NA
XANPAGTX0501_002271-T1	IPR007889	IPR	DNA binding HTH domain, Psq-type	Transcription factors	Expression regulation	0.0000000	0.0000000	1.266656	0.0825632	7.7099775	0.4493197	0.0005639	0.0473879	0.0419356	0.0473879	culture	hypothetical protein	NA	S:(S) Function unknown	ENOG503NY4S	GO_function: GO:0003677 - DNA binding [Evidence IEA]	IPR006600 HTH CenpB-type DNA-binding domain, IPR007889 DNA binding HTH domain, Psq-type, IPR009057 Homeobox-like domain superfamily	PF03221, PF04218	NA	NA
XANPAGTX0501_002762-T1	IPR021858	IPR	Fungal transcription factor	Transcription factors	Expression regulation	0.0000000	0.0000000	1.105893	0.1534317	8.3370387	0.4669427	0.0003147	0.1652861	0.0507401	0.1652861	culture	DNA-binding transcriptional regulator ume6	NA	S:(S) Function unknown	ENOG503P0WT	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR021858 Fungal transcription factor, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00172, PF11951	NA	NA	K09243
XANPAGTX0501_002762-T1	IPR036864	IPR	Zn(2)-C6 fungal-type DNA-binding domain superfamily	Transcription factors	Expression regulation	0.0000000	0.0000000	1.105893	0.1534317	8.3370387	0.4669427	0.0003147	0.1652861	0.0507401	0.1652861	culture	DNA-binding transcriptional regulator ume6	NA	S:(S) Function unknown	ENOG503P0WT	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR021858 Fungal transcription factor, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00172, PF11951	NA	NA	K09243
XANPAGTX0501_005120-T1	IPR036864	IPR	Zn(2)-C6 fungal-type DNA-binding domain superfamily	Transcription factors	Expression regulation	0.0000000	0.0000000	5.474386	0.7033726	2.6580884	10.8850322	0.0235528	3.4566378	0.8925553	3.4566378	culture	hypothetical protein	NA	NA	NA	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00172	NA	NA
XANPAGTX0501_005479-T1	IPR013083	IPR	Zinc finger, RING/FYVE/PHD-type	Transcription factors	Expression regulation	0.0038642	0.0092498	2.092073	0.7241406	4.9190414	4.6565807	0.2622592	3.4264802	0.2161907	3.4264802	culture	peroxisome bioproteinsis factor 10	NA	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NWSD	NA	IPR001841 Zinc finger, RING-type, IPR006845 Pex, N-terminal, IPR013083 Zinc finger, RING/FYVE/PHD-type, IPR017907 Zinc finger, RING-type, conserved site	PF00097, PF04757, PF13445, PF13639, PF13920, PF13923, PF14447, PF14634	NA	NA	K13346
XANPAGTX0501_005608-T1	IPR021858	IPR	Fungal transcription factor	Transcription factors	Expression regulation	0.0218088	0.0422590	2.365288	1.0312188	4.6186652	8.6189288	0.0182522	7.4623026	0.2767044	7.4623026	culture	hypothetical protein	NA	S:(S) Function unknown	ENOG503P4SS	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR021858 Fungal transcription factor, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00172, PF11951	NA	NA	K09246
XANPAGTX0501_005608-T1	IPR036864	IPR	Zn(2)-C6 fungal-type DNA-binding domain superfamily	Transcription factors	Expression regulation	0.0218088	0.0422590	2.365288	1.0312188	4.6186652	8.6189288	0.0182522	7.4623026	0.2767044	7.4623026	culture	hypothetical protein	NA	S:(S) Function unknown	ENOG503P4SS	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR021858 Fungal transcription factor, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00172, PF11951	NA	NA	K09246
XANPAGTX0501_005640-T1	IPR013087	IPR	Zinc finger C2H2-type	Transcription factors	Expression regulation	0.0000000	0.0000000	2.983823	0.3506931	3.0708697	2.8001851	0.1211909	0.4630966	0.7439497	0.7439497	culture	hypothetical protein	NA	NA	NA	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA]	IPR013087 Zinc finger C2H2-type	NA	NA	NA
XANPAGTX0501_006285-T1	IPR036864	IPR	Zn(2)-C6 fungal-type DNA-binding domain superfamily	Transcription factors	Expression regulation	0.0000000	0.0000000	1.232296	0.2060539	4.5818951	0.5728451	0.0136747	0.1847482	0.2849969	0.2849969	culture	hypothetical protein	NA	E:(E) Amino acid transport and metabolism	ENOG503P05H	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0005515 - protein binding [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_function: GO:0016407 - acetyltransferase activity [Evidence IEA], GO_function: GO:0016740 - transferase activity [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR001451 Hexapeptide repeat, IPR002110 Ankyrin repeat, IPR011004 Trimeric LpxA-like superfamily, IPR018357 Hexapeptide transferase, conserved site, IPR020683 Domain of unknown function DUF3447, IPR024688 Maltose/galactoside acetyltransferase, IPR036770 Ankyrin repeat-containing domain superfamily, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00023, PF00132, PF00172, PF12464, PF12796, PF13606, PF13637, PF14602	NA	NA
XANPAGTX0501_006288-T1	IPR036864	IPR	Zn(2)-C6 fungal-type DNA-binding domain superfamily	Transcription factors	Expression regulation	0.0000218	0.0000875	1.565553	0.3687436	2.8277492	0.9947942	0.1253556	0.2677195	0.8311362	0.8311362	culture	hypothetical protein	NA	E:(E) Amino acid transport and metabolism	ENOG503P05H	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0005515 - protein binding [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_function: GO:0016407 - acetyltransferase activity [Evidence IEA], GO_function: GO:0016740 - transferase activity [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR001451 Hexapeptide repeat, IPR002110 Ankyrin repeat, IPR011004 Trimeric LpxA-like superfamily, IPR018357 Hexapeptide transferase, conserved site, IPR020683 Domain of unknown function DUF3447, IPR024688 Maltose/galactoside acetyltransferase, IPR036770 Ankyrin repeat-containing domain superfamily, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00023, PF00132, PF00172, PF12464, PF12796, PF13606, PF13637, PF14602	NA	NA
XANPAGTX0501_007781-T1	IPR036638	IPR	Helix-loop-helix DNA-binding domain superfamily	Transcription factors	Expression regulation	0.0000000	0.0000000	1.266304	0.1277506	7.0722930	0.5135607	0.0010537	0.1137507	0.0452223	0.1137507	culture	basic helix-loop-helix protein	NA	K:(K) Transcription	ENOG503P143	GO_function: GO:0046983 - protein dimerization activity [Evidence IEA]	IPR011598 Myc-type, basic helix-loop-helix (bHLH) domain, IPR036638 Helix-loop-helix DNA-binding domain superfamily	PF00010	NA	NA	K22484
XANPAGTX0501_009300-T1	IPR021858	IPR	Fungal transcription factor	Transcription factors	Expression regulation	0.0050968	0.0117893	1.743077	0.6223389	3.5696174	3.3905126	0.5046854	2.2198096	0.5726596	2.2198096	culture	hypothetical protein	NA	NA	NA	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR021858 Fungal transcription factor, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00172, PF11951	NA	NA
XANPAGTX0501_009300-T1	IPR036864	IPR	Zn(2)-C6 fungal-type DNA-binding domain superfamily	Transcription factors	Expression regulation	0.0050968	0.0117893	1.743077	0.6223389	3.5696174	3.3905126	0.5046854	2.2198096	0.5726596	2.2198096	culture	hypothetical protein	NA	NA	NA	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR021858 Fungal transcription factor, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00172, PF11951	NA	NA
XANPAGTX0501_009446-T1	IPR004827	IPR	Basic-leucine zipper domain	Transcription factors	Expression regulation	0.0000000	0.0000000	1.336363	0.1955910	9.7535998	0.7081652	0.0000855	0.2690246	0.1103202	0.2690246	culture	hypothetical protein	NA	NA	NA	GO_function: GO:0003700 - DNA-binding transcription factor activity [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR004827 Basic-leucine zipper domain	NA	NA	NA
XANPAGTX0501_010541-T1	IPR036864	IPR	Zn(2)-C6 fungal-type DNA-binding domain superfamily	Transcription factors	Expression regulation	0.0244091	0.0466465	1.086108	0.4825798	0.7427463	1.5999442	0.1650016	1.1868632	1.4732119	1.4732119	culture	hypothetical protein	NA	NA	NA	GO_component: GO:0005634 - nucleus [Evidence IEA], GO_function: GO:0000981 - DNA-binding transcription factor activity, RNA polymerase II-specific [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_process: GO:0006355 - regulation of transcription, DNA-templated [Evidence IEA]	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	PF00172	NA	NA
XANPAGTX0501_000794-T1	IPR001465	IPR	Malate synthase	Acetyl-CoA production and metabolism	Fungal multicellularity	0.0000000	0.0000000	1.279442	0.1432048	8.0999208	0.5503675	0.0003896	0.1438709	0.0465651	0.1438709	culture	hypothetical protein	NA	H:(H) Coenzyme transport and metabolism	ENOG503NX6Q	GO_function: GO:0003824 - catalytic activity [Evidence IEA], GO_function: GO:0004474 - malate synthase activity [Evidence IEA], GO_process: GO:0006097 - glyoxylate cycle [Evidence IEA]	IPR001465 Malate synthase, IPR006252 Malate synthase A, IPR011076 Malate synthase superfamily, IPR019830 Malate synthase, conserved site	PF01274	NA	NA	K01638
XANPAGTX0501_001977-T1	IPR013149	IPR	Alcohol dehydrogenase-like, C-terminal	Acetyl-CoA production and metabolism	Fungal multicellularity	0.0000000	0.0000000	2.778744	0.4070786	9.5305427	3.0639356	0.0002904	1.1654145	0.0952094	1.1654145	culture	hypothetical protein	NA	C:(C) Energy production and conversion	ENOG503NX3C, ENOG503NXT7	GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR011032 GroES-like superfamily, IPR013149 Alcohol dehydrogenase-like, C-terminal, IPR020843 Polyketide synthase, enoylreductase domain, IPR036291 NAD(P)-binding domain superfamily	PF00107	NA	NA
XANPAGTX0501_002322-T1	IPR013149	IPR	Alcohol dehydrogenase-like, C-terminal	Acetyl-CoA production and metabolism	Fungal multicellularity	0.0000000	0.0000000	1.174252	0.1797157	8.2422637	0.5654985	0.0003455	0.2268523	0.0489419	0.2268523	culture	hypothetical protein	NA	Q:(Q) Secondary metabolites biosynthesis, transport and catabolism	ENOG503NXYU	GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR002328 Alcohol dehydrogenase, zinc-type, conserved site, IPR011032 GroES-like superfamily, IPR013149 Alcohol dehydrogenase-like, C-terminal, IPR013154 Alcohol dehydrogenase-like, N-terminal, IPR036291 NAD(P)-binding domain superfamily	PF00107, PF08240	NA	NA
XANPAGTX0501_003177-T1	IPR013149	IPR	Alcohol dehydrogenase-like, C-terminal	Acetyl-CoA production and metabolism	Fungal multicellularity	0.0002440	0.0007823	3.018453	0.8228144	3.7122101	6.8814065	0.0392819	4.7232290	0.5265193	4.7232290	culture	hypothetical protein	NA	I:(I) Lipid transport and metabolism	ENOG503NWJ7	GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_function: GO:0031177 - phosphopantetheine binding [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR006162 Phosphopantetheine attachment site, IPR009081 Phosphopantetheine binding ACP domain, IPR011032 GroES-like superfamily, IPR013149 Alcohol dehydrogenase-like, C-terminal, IPR013217 Methyltransferase type 12, IPR013968 Polyketide synthase, ketoreductase domain, IPR020806 Polyketide synthase, phosphopantetheine-binding domain, IPR020843 Polyketide synthase, enoylreductase domain, IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily, IPR036291 NAD(P)-binding domain superfamily, IPR036736 ACP-like superfamily	PF00106, PF00107, PF00550, PF01209, PF08241, PF08242, PF08659, PF13489, PF13649, PF13847	NA	NA
XANPAGTX0501_003454-T1	IPR006254	IPR	Isocitrate lyase	Acetyl-CoA production and metabolism	Fungal multicellularity	0.0000000	0.0000000	1.351773	0.1455668	7.4637810	0.6028082	0.0007292	0.1483293	0.0412605	0.1483293	culture	isocitrate lyase 1	NA	C:(C) Energy production and conversion	ENOG503NUMX	GO_function: GO:0003824 - catalytic activity [Evidence IEA], GO_function: GO:0004451 - isocitrate lyase activity [Evidence IEA], GO_process: GO:0019752 - carboxylic acid metabolic process [Evidence IEA]	IPR006254 Isocitrate lyase, IPR015813 Pyruvate/Phosphoenolpyruvate kinase-like domain superfamily, IPR018523 Isocitrate lyase/phosphorylmutase, conserved site, IPR040442 Pyruvate kinase-like domain superfamily	PF00463, PF13714	NA	NA	K01637
XANPAGTX0501_004396-T1	IPR015590	IPR	Aldehyde dehydrogenase domain	Acetyl-CoA production and metabolism	Fungal multicellularity	0.0000000	0.0000000	1.116906	0.1874301	9.6043109	0.5517022	0.0000885	0.2470333	0.0998782	0.2470333	culture	aldehyde dehydrogenase (NAD(P)(+)) ald5	NA	C:(C) Energy production and conversion	ENOG503NW4N	GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_function: GO:0016620 - oxidoreductase activity, acting on the aldehyde or oxo group of donors, NAD or NADP as acceptor [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR015590 Aldehyde dehydrogenase domain, IPR016160 Aldehyde dehydrogenase, cysteine active site, IPR016161 Aldehyde/histidinol dehydrogenase, IPR016162 Aldehyde dehydrogenase, N-terminal, IPR016163 Aldehyde dehydrogenase, C-terminal, IPR029510 Aldehyde dehydrogenase, glutamic acid active site	PF00171	NA	NA	K00128
XANPAGTX0501_004470-T1	IPR013149	IPR	Alcohol dehydrogenase-like, C-terminal	Acetyl-CoA production and metabolism	Fungal multicellularity	0.0000000	0.0000000	1.987506	0.2441858	8.7071041	1.3968726	0.0003142	0.4191289	0.0596771	0.4191289	culture	Alcohol dehydrogenase	NA	Q:(Q) Secondary metabolites biosynthesis, transport and catabolism	ENOG503NW0B, ENOG503P137	GO_function: GO:0008270 - zinc ion binding [Evidence IEA], GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR002328 Alcohol dehydrogenase, zinc-type, conserved site, IPR011032 GroES-like superfamily, IPR013149 Alcohol dehydrogenase-like, C-terminal, IPR013154 Alcohol dehydrogenase-like, N-terminal, IPR020843 Polyketide synthase, enoylreductase domain, IPR036291 NAD(P)-binding domain superfamily	PF00107, PF08240, PF13602	NA	NA	K13953
XANPAGTX0501_004953-T1	IPR001765	IPR	Carbonic anhydrase	Acetyl-CoA production and metabolism	Fungal multicellularity	0.0000010	0.0000051	1.251062	0.2554861	4.0278491	0.6641582	0.0289293	0.2520473	0.4302336	0.4302336	culture	hypothetical protein	NA	H:(H) Coenzyme transport and metabolism	ENOG503P2JY, ENOG503Q3DE	GO_function: GO:0004089 - carbonate dehydratase activity [Evidence IEA], GO_function: GO:0008270 - zinc ion binding [Evidence IEA]	IPR001765 Carbonic anhydrase, IPR036874 Carbonic anhydrase superfamily	PF00484	NA	NA
XANPAGTX0501_006078-T1	IPR011904	IPR	Acetate-CoA ligase	Acetyl-CoA production and metabolism	Fungal multicellularity	0.0000000	0.0000000	1.027435	0.1147023	8.9315111	0.3544505	0.0001566	0.0923934	0.0668719	0.0923934	culture	acetyl-coenzyme A synthetase 2	NA	I:(I) Lipid transport and metabolism	ENOG503NUTI	GO_function: GO:0003824 - catalytic activity [Evidence IEA], GO_function: GO:0003987 - acetate-CoA ligase activity [Evidence IEA], GO_function: GO:0016208 - AMP binding [Evidence IEA], GO_process: GO:0019427 - acetyl-CoA biosynthetic process from acetate [Evidence IEA]	IPR000873 AMP-dependent synthetase/ligase domain, IPR011904 Acetate-CoA ligase, IPR020845 AMP-binding, conserved site, IPR025110 AMP-binding enzyme, C-terminal domain, IPR032387 Acetyl-coenzyme A synthetase, N-terminal domain, IPR042099 ANL, N-terminal domain	PF00501, PF13193, PF16177	NA	NA	K01895
XANPAGTX0501_009391-T1	IPR015590	IPR	Aldehyde dehydrogenase domain	Acetyl-CoA production and metabolism	Fungal multicellularity	0.0000000	0.0000000	1.331192	0.2125148	7.3700053	0.7515491	0.0350145	0.2826807	0.0415771	0.2826807	culture	1-pyrroline-5-carboxylate dehydrogenase	NA	E:(E) Amino acid transport and metabolism	ENOG503NWNB, ENOG503NZ2H	GO_function: GO:0003842 - 1-pyrroline-5-carboxylate dehydrogenase activity [Evidence IEA], GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_function: GO:0016620 - oxidoreductase activity, acting on the aldehyde or oxo group of donors, NAD or NADP as acceptor [Evidence IEA], GO_process: GO:0010133 - proline catabolic process to glutamate [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR005931 Delta-1-pyrroline-5-carboxylate dehydrogenase, IPR015590 Aldehyde dehydrogenase domain, IPR016160 Aldehyde dehydrogenase, cysteine active site, IPR016161 Aldehyde/histidinol dehydrogenase, IPR016162 Aldehyde dehydrogenase, N-terminal, IPR016163 Aldehyde dehydrogenase, C-terminal, IPR029510 Aldehyde dehydrogenase, glutamic acid active site	PF00171	NA	NA	K00294
XANPAGTX0501_005060-T1	IPR000772	IPR	Ricin B, lectin domain	Cell surface and cell wall proteins	Fungal multicellularity	0.0047741	0.0111313	1.802595	0.6387892	1.7832782	3.5842554	0.0385866	2.8318457	1.1987617	2.8318457	culture	hypothetical protein	NA	NA	NA	NA	IPR000772 Ricin B, lectin domain, IPR035992 Ricin B-like lectins	NA	NA	SignalP(1-20,cutsite=SFS-DI,prob=0.7168), SignalP(1-21,cutsite=VAS-LI,prob=0.3541), SignalP(1-24,cutsite=ASA-AI,prob=0.5941)
XANPAGTX0501_001051-T1	GH17	CAZy	beta-1,3-glucanase, beta-1,3-glucosidase	Cell wall remodeling	Fungal multicellularity	0.0000000	0.0000000	1.077085	0.1225353	7.1518772	0.3933065	0.0009718	0.1046503	0.0439181	0.1046503	culture	hypothetical protein	GH17	G:(G) Carbohydrate transport and metabolism	ENOG503NXKT	NA	IPR017853 Glycoside hydrolase superfamily	NA	NA	SignalP(1-18,cutsite=SVA-SS,prob=0.3042)
XANPAGTX0501_001594-T2	IPR000217	IPR	Tubulin	Cytoskeleton	Fungal multicellularity	0.0017979	0.0047179	1.411216	0.4520623	3.7508395	1.8865624	0.2802533	1.1573159	0.5142858	1.1573159	culture	gamma-tubulin, variant 2	NA	Z:(Z) Cytoskeleton	ENOG503NWWN	GO_component: GO:0000930 - gamma-tubulin complex [Evidence IEA], GO_component: GO:0005874 - microtubule [Evidence IEA], GO_function: GO:0003924 - GTPase activity [Evidence IEA], GO_function: GO:0005525 - GTP binding [Evidence IEA], GO_process: GO:0007017 - microtubule-based process [Evidence IEA], GO_process: GO:0007020 - microtubule nucleation [Evidence IEA], GO_process: GO:0031122 - cytoplasmic microtubule organization [Evidence IEA]	IPR000217 Tubulin, IPR002454 Gamma tubulin, IPR003008 Tubulin/FtsZ, GTPase domain, IPR008280 Tubulin/FtsZ, C-terminal, IPR017975 Tubulin, conserved site, IPR018316 Tubulin/FtsZ, 2-layer sandwich domain, IPR023123 Tubulin, C-terminal, IPR036525 Tubulin/FtsZ, GTPase domain superfamily, IPR037103 Tubulin/FtsZ-like, C-terminal domain	PF00091, PF03953, PF10644	NA	NA
XANPAGTX0501_009715-T1	IPR021765	IPR	Mycotoxin biosynthesis protein UstYa-like	Defense	Fungal multicellularity	0.0167701	0.0336585	2.760824	1.1543310	4.7136281	10.9534712	0.0061775	9.3671312	0.2561715	9.3671312	culture	hypothetical protein	NA	S:(S) Function unknown	ENOG503P6KY	GO_process: GO:0043386 - mycotoxin biosynthetic process [Evidence IEA]	IPR021765 Mycotoxin biosynthesis protein UstYa-like	PF11807	NA	NA
XANPAGTX0501_009716-T1	IPR021765	IPR	Mycotoxin biosynthesis protein UstYa-like	Defense	Fungal multicellularity	0.0108486	0.0229604	2.958263	1.1612237	4.7266442	11.3454171	0.0189124	9.4666681	0.2534575	9.4666681	culture	hypothetical protein	NA	NA	NA	GO_process: GO:0043386 - mycotoxin biosynthetic process [Evidence IEA]	IPR021765 Mycotoxin biosynthesis protein UstYa-like	PF11807	NA	NA
XANPAGTX0501_008060-T1	IPR002225	IPR	3-beta hydroxysteroid dehydrogenase/isomerase	Lipid metabolism	Fungal multicellularity	0.0028569	0.0071309	1.072679	0.3596294	7.2002267	1.1663770	0.0013481	0.9084446	0.0432273	0.9084446	culture	hypothetical protein	NA	E:(E) Amino acid transport and metabolism, G:(G) Carbohydrate transport and metabolism, I:(I) Lipid transport and metabolism, M:(M) Cell wall/membrane/envelope biogenesis	ENOG503NWMM, ENOG50KOG1430	GO_function: GO:0003854 - 3-beta-hydroxy-delta5-steroid dehydrogenase activity [Evidence IEA], GO_function: GO:0016616 - oxidoreductase activity, acting on the CH-OH group of donors, NAD or NADP as acceptor [Evidence IEA], GO_process: GO:0006694 - steroid biosynthetic process [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR002225 3-beta hydroxysteroid dehydrogenase/isomerase, IPR036291 NAD(P)-binding domain superfamily	PF01073, PF01370, PF04321, PF07993, PF08659, PF16363	NA	NA
XANPAGTX0501_000658-T1	IPR001810	IPR	F-box domain	Protein ubiquitination	Fungal multicellularity	0.0000000	0.0000000	1.036915	0.1686236	5.4015689	0.4629969	0.0060300	0.1939880	0.1455484	0.1939880	culture	hypothetical protein	NA	NA	NA	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR001810 F-box domain, IPR032675 Leucine-rich repeat domain superfamily, IPR036047 F-box-like domain superfamily	PF12937	NA	NA
XANPAGTX0501_001643-T1	IPR001810	IPR	F-box domain	Protein ubiquitination	Fungal multicellularity	0.0000000	0.0000000	3.021633	0.3426756	4.8866173	3.0903449	0.0393202	0.7867148	0.2220969	0.7867148	culture	hypothetical protein	NA	NA	NA	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR001810 F-box domain, IPR032675 Leucine-rich repeat domain superfamily, IPR036047 F-box-like domain superfamily	PF12937	NA	NA
XANPAGTX0501_005479-T1	IPR017907	IPR	Zinc finger; RING-type; conserved site	Protein ubiquitination	Fungal multicellularity	0.0038642	0.0092498	2.092073	0.7241406	4.9190414	4.6565807	0.2622592	3.4264802	0.2161907	3.4264802	culture	peroxisome bioproteinsis factor 10	NA	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NWSD	NA	IPR001841 Zinc finger, RING-type, IPR006845 Pex, N-terminal, IPR013083 Zinc finger, RING/FYVE/PHD-type, IPR017907 Zinc finger, RING-type, conserved site	PF00097, PF04757, PF13445, PF13639, PF13920, PF13923, PF14447, PF14634	NA	NA	K13346
XANPAGTX0501_005769-T1	IPR001810	IPR	F-box domain	Protein ubiquitination	Fungal multicellularity	0.0028308	0.0070738	2.146850	0.7190834	3.7395999	4.6654076	0.0534970	3.5839002	0.5178331	3.5839002	culture	hypothetical protein	NA	NA	NA	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR001810 F-box domain, IPR036047 F-box-like domain superfamily	PF12937	NA	NA
XANPAGTX0501_000832-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	1.505444	0.1426654	6.3864016	0.7074437	0.0022068	0.1409689	0.0698868	0.1409689	culture	hypothetical protein	NA	G:(G) Carbohydrate transport and metabolism	ENOG503NZKN	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_001050-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	1.429018	0.1651053	8.2569814	0.6979474	0.0003178	0.1914405	0.0492095	0.1914405	culture	Plasma membrane low glucose sensor	NA	P:(P) Inorganic ion transport and metabolism	ENOG503NU51	GO_component: GO:0016020 - membrane [Evidence IEA], GO_component: GO:0016021 - integral component of membrane [Evidence IEA], GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF00083, PF07690	NA	NA	K08139
XANPAGTX0501_002002-T1	IPR023271	IPR	Aquaporin-like	Transporters	Fungal multicellularity	0.0000000	0.0000000	1.049871	0.1622478	7.5069568	0.4554792	0.0007006	0.1844775	0.0412267	0.1844775	culture	Aquaporin-1	NA	P:(P) Inorganic ion transport and metabolism	ENOG503NV37	GO_component: GO:0016020 - membrane [Evidence IEA], GO_function: GO:0015267 - channel activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR000425 Major intrinsic protein, IPR023271 Aquaporin-like	PF00230	NA	NA	K09866
XANPAGTX0501_004029-T1	IPR023271	IPR	Aquaporin-like	Transporters	Fungal multicellularity	0.0000000	0.0000000	2.052872	0.1878492	7.5330379	1.2981236	0.0009361	0.2472920	0.0412382	0.2472920	culture	glycerol channel	NA	P:(P) Inorganic ion transport and metabolism	ENOG503NY8M, ENOG503NZK7	GO_component: GO:0016020 - membrane [Evidence IEA], GO_function: GO:0015267 - channel activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR000425 Major intrinsic protein, IPR023271 Aquaporin-like	PF00230	NA	NA	K09876
XANPAGTX0501_004440-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000185	0.0000755	1.853001	0.4327509	4.9706372	2.1329539	0.0142949	1.3030764	0.2071035	1.3030764	culture	hypothetical protein	NA	J:(J) Translation, ribosomal structure and biogenesis, S:(S) Function unknown	ENOG503P3D5, ENOG503P53R, ENOG503P672, ENOG503PACP, ENOG503PAGX, ENOG503PEB6, ENOG503PEZW, ENOG503PU88	NA	IPR036259 MFS transporter superfamily	NA	NA	NA
XANPAGTX0501_005016-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	1.832070	0.1094530	9.3333982	0.9097109	0.0001279	0.0687911	0.0841450	0.0841450	culture	hypothetical protein	NA	P:(P) Inorganic ion transport and metabolism	ENOG503NU51	GO_component: GO:0016020 - membrane [Evidence IEA], GO_component: GO:0016021 - integral component of membrane [Evidence IEA], GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF00083, PF07690	NA	NA	K24193
XANPAGTX0501_005044-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	1.071341	0.1202834	7.9348128	0.3864969	0.0004076	0.1013680	0.0442533	0.1013680	culture	hypothetical protein	NA	G:(G) Carbohydrate transport and metabolism	ENOG503NU3S	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA	K08192
XANPAGTX0501_005408-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000017	0.0000085	1.897102	0.3964036	8.8996342	1.9700731	0.0004314	1.1049377	0.0657554	1.1049377	culture	hypothetical protein	NA	J:(J) Translation, ribosomal structure and biogenesis, S:(S) Function unknown	ENOG503P3D5, ENOG503P53R, ENOG503P672, ENOG503PACP, ENOG503PAGX, ENOG503PEB6, ENOG503PEZW, ENOG503PU88	NA	IPR036259 MFS transporter superfamily	NA	NA	NA
XANPAGTX0501_005560-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	1.238528	0.1588486	8.2620088	0.5565382	0.0003310	0.1771693	0.0493018	0.1771693	culture	hypothetical protein	NA	G:(G) Carbohydrate transport and metabolism	ENOG503NU7U	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA	K08192
XANPAGTX0501_007295-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	2.582166	0.2893330	8.0748945	2.2429571	0.0008266	0.5880551	0.0461851	0.5880551	culture	hypothetical protein	NA	U:(U) Intracellular trafficking, secretion, and vesicular transport	ENOG503NUAW	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF06609, PF07690	NA	NA
XANPAGTX0501_008064-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0109967	0.0232297	2.949333	1.1598747	4.6633260	11.3109259	0.1759259	9.2876298	0.2668881	9.2876298	culture	hypothetical protein	NA	U:(U) Intracellular trafficking, secretion, and vesicular transport	ENOG503PBXT	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA	K03446
XANPAGTX0501_008356-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	2.226797	0.1933245	8.2641542	1.4992825	0.0004763	0.2624330	0.0493414	0.2624330	culture	hypothetical protein	NA	U:(U) Intracellular trafficking, secretion, and vesicular transport	ENOG503NU0V	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_008371-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	1.286354	0.2212317	7.9678823	0.7477105	0.0004654	0.3438265	0.0446802	0.3438265	culture	hypothetical protein	NA	G:(G) Carbohydrate transport and metabolism	ENOG503NWTF	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_008605-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	1.064936	0.1381258	7.8216369	0.4143346	0.0005126	0.1336964	0.0429223	0.1336964	culture	hypothetical protein	NA	S:(S) Function unknown	ENOG503NU8J	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_008674-T2	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0001443	0.0004860	2.269438	0.5971204	1.4678145	3.7125170	0.8267209	1.6814437	1.2966119	1.6814437	culture	hypothetical protein	NA	S:(S) Function unknown	ENOG503NUV5	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_008702-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	1.818935	0.1767878	6.4667715	1.0432086	0.0022300	0.2176252	0.0657147	0.2176252	culture	hypothetical protein	NA	G:(G) Carbohydrate transport and metabolism	ENOG503NX5J	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR036259 MFS transporter superfamily	PF07690	NA	NA	K02429
XANPAGTX0501_009071-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	2.192024	0.1882362	8.2567367	1.4475099	0.0004736	0.2487783	0.0492050	0.2487783	culture	hypothetical protein	NA	S:(S) Function unknown	ENOG503NTW3, ENOG503P0ME	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_009168-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0085859	0.0186420	1.995118	0.7591441	4.5723593	4.9092125	0.0047972	4.0491738	0.2871781	4.0491738	culture	hypothetical protein	NA	S:(S) Function unknown	ENOG503NTXQ	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	NA	NA	NA
XANPAGTX0501_009169-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0081329	0.0177963	1.799551	0.6799737	4.3264627	3.9499177	0.0241530	3.2283407	0.3475984	3.2283407	culture	hypothetical protein	NA	S:(S) Function unknown	ENOG503NTXQ	NA	IPR036259 MFS transporter superfamily	NA	NA	NA
XANPAGTX0501_009291-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0000000	0.0000000	1.371945	0.1743963	6.6002754	0.6791824	0.0017389	0.2122083	0.0597119	0.2122083	culture	hypothetical protein	NA	J:(J) Translation, ribosomal structure and biogenesis, S:(S) Function unknown	ENOG503P3D5, ENOG503P53R, ENOG503P672, ENOG503PACP, ENOG503PAGX, ENOG503PEB6, ENOG503PEZW, ENOG503PU88	NA	IPR036259 MFS transporter superfamily	NA	NA	NA
XANPAGTX0501_009737-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0029463	0.0073284	1.345421	0.4525023	1.5872793	1.4106490	0.1796187	0.8116649	1.2607503	1.2607503	culture	hypothetical protein	NA	S:(S) Function unknown	ENOG503NU52, ENOG503PB8X	GO_component: GO:0016021 - integral component of membrane [Evidence IEA], GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR005829 Sugar transporter, conserved site, IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	SignalP(1-23,cutsite=LLT-DL,prob=0.2037)
XANPAGTX0501_010318-T2	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0024572	0.0062342	1.063673	0.3512139	5.3899201	1.1209658	0.1569708	0.7107412	0.1468926	0.7107412	culture	hypothetical protein	NA	U:(U) Intracellular trafficking, secretion, and vesicular transport	ENOG503NY43	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_010563-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0017357	0.0045752	2.597890	0.8294464	4.9843134	6.3623200	0.0072535	4.8323392	0.2047585	4.8323392	culture	hypothetical protein	NA	S:(S) Function unknown	ENOG503NZPM, ENOG503P0C6	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_010564-T1	IPR036259	IPR	MFS transporter superfamily	Transporters	Fungal multicellularity	0.0022634	0.0057834	2.625398	0.8598554	5.7024367	6.7468722	0.0199212	5.1810323	0.1155923	5.1810323	culture	hypothetical protein	NA	S:(S) Function unknown	ENOG503NZPM, ENOG503P0C6	GO_function: GO:0022857 - transmembrane transporter activity [Evidence IEA], GO_process: GO:0055085 - transmembrane transport [Evidence IEA]	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	PF07690	NA	NA
XANPAGTX0501_008837-T2	K11238	KEGG	BNI1; cytokinesis protein	MAPK signaling pathway	Signal transduction	0.0000000	0.0000001	1.779571	0.3147680	5.5192793	1.4676948	0.3292317	0.3677369	0.1328148	0.3677369	culture	hypothetical protein	NA	T:(T) Signal transduction mechanisms, Z:(Z) Cytoskeleton	ENOG503NU2F	GO_function: GO:0003779 - actin binding [Evidence IEA], GO_function: GO:0017048 - Rho GTPase binding [Evidence IEA], GO_process: GO:0016043 - cellular component organization [Evidence IEA], GO_process: GO:0030036 - actin cytoskeleton organization [Evidence IEA]	IPR010472 Formin, FH3 domain, IPR010473 Formin, GTPase-binding domain, IPR011989 Armadillo-like helical, IPR014767 Diaphanous autoregulatory (DAD) domain, IPR014768 Rho GTPase-binding/formin homology 3 (GBD/FH3) domain, IPR015425 Formin, FH2 domain, IPR016024 Armadillo-type fold, IPR042201 Formin, FH2 domain superfamily	PF02181, PF06367, PF06371	NA	NA	K11238

• In lichens, among the upregulated are transporters, TFs, protein ubiquitination, and cell division

mult_gene_table_lichen %>% group_by(Function) %>% summarise(n=n()) %>% arrange(desc(n))

## # A tibble: 20 × 2
##    Function                                      n
##    <chr>                                     <int>
##  1 "Transporters"                               27
##  2 "Transcription factors"                      23
##  3 "Protein ubiquitination"                     14
##  4 "Cell division, proliferation and growth"    12
##  5 "Cell wall remodeling"                       10
##  6 "Cell surface and cell wall proteins"         9
##  7 "RNA binding proteins"                        5
##  8 "Acetyl-CoA production and metabolism"        4
##  9 "Defense"                                     3
## 10 "Lipid metabolism"                            3
## 11 "RNA interference"                            3
## 12 "Cell wall misc"                              2
## 13 "Oxylipins"                                   2
## 14 "Velvet"                                      2
## 15 "Carbohydrate storage"                        1
## 16 "Cell wall biosynthesis "                     1
## 17 "G-proteins and GPCR"                         1
## 18 "MAPK signaling pathway"                      1
## 19 "Ribosomal genes"                             1
## 20 "Stress response genes"                       1

• In culture, transporters and TFs are also on the top of the list.

mult_gene_table_culture %>% group_by(Function) %>% summarise(n=n()) %>% arrange(desc(n))

## # A tibble: 11 × 2
##    Function                                 n
##    <chr>                                <int>
##  1 Transporters                            24
##  2 Transcription factors                   17
##  3 Acetyl-CoA production and metabolism    10
##  4 Protein ubiquitination                   4
##  5 Defense                                  2
##  6 RNA binding proteins                     2
##  7 Cell surface and cell wall proteins      1
##  8 Cell wall remodeling                     1
##  9 Cytoskeleton                             1
## 10 Lipid metabolism                         1
## 11 MAPK signaling pathway                   1

• Notable differences:
  • Cell division, proliferation and growth are on the 4th place in the lichen list, but are absent from the culture list
  • Cell wall-related proteins upregulated in lichens and almost not in cultures
  • Both genes potentially linked to oxylipin biosynthesis are upregulated in lichens
  • 2 out of 5 genes with the Velvet domain are upregulated in lichens. None are in cultures
  • Both lists contain mycotoxin biosynthesis proteins, but different ones
• Weirdly, almost no ‘traditional’ signalling pathway genes are upregulated. In each list, we have one MAPK-pathway gene upregulated
  • In lichen, it’s tyrosine-protein phosphatase 2/3 (K19806), which according to KEGG annotations acts on MAPK
  • In culture, it’s BNI1, a cytokinesis protein (K11238)
• Heatmap showing expression of all multicellularity-related proteins

png("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_multi_all.png",res=300,width=2000,height=1500)
plot_transcript_heatmap(so, transcripts=mult_gene_list,cluster_transcripts=T,show_rownames
=F)
dev.off()

## pdf 
##   4

knitr::include_graphics("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_multi_all.png")

• Heatmap showing expression of DGE multicellularity-related proteins
  • Added an annotation track showing functions. NB: some genes had more than one relevant annotation! In cases where one gene had >1 function, I picked one function to show here. Selection was either based on which function had more annotations. If there were multiple functions with the same number of annotations, picked one randomly
  • Saved the annotation file as analysis_and_temp_files/08_dge_culture_lichen/multicell_to_genes.txt
• Here, highlighting Cell division proteins

library(RColorBrewer)
#define annotation for gene functions
annotation<-mult_gene_table %>% group_by(TranscriptID,Function)%>% summarize(n=n()) %>%
  group_by(Function,TranscriptID) %>% dplyr::slice(which.max(n)) %>% 
  group_by(TranscriptID) %>% sample_n(1) %>% select(-n) %>%
  data.frame() %>% left_join(mult_sig,by=c("TranscriptID"="target_id"))
write.table(annotation,"../analysis_and_temp_files/08_dge_culture_lichen/multicell_to_genes.txt", sep = "\t", quote=F, row.names = F)
annotation<-annotation %>% filter(TranscriptID %in% mult_sig$target_id[mult_sig$change!="low_logFC"])
rownames(annotation)<-annotation$TranscriptID
annotation$Function<-as.factor(annotation$Function)
annotation_vector<-annotation %>% select(Function)
#pick colors
ann_colors = list(
    condition = c("lichen_thallus"="#F8766D","xanthoria_culture"="#619CFF"),
    Function = c("Transcription factors"="grey",
                 "Transporters"="grey",
                 "Protein ubiquitination"="grey",
                 "Cell division, proliferation and growth"=brewer.pal(n = 8, name = "Dark2")[4],
                 "Acetyl-CoA production and metabolism"="grey",
                 "Cell surface and cell wall proteins"="grey",
                 "Cell wall remodeling"="grey",
                 "Velvet"="grey","Stress response genes"="grey","RNA interference"="grey",
                 "RNA binding proteins"="grey","Ribosomal genes"="grey","Oxylipins"="grey",
                 "MAPK signaling pathway"="grey","Lipid metabolism"="grey","G-proteins and GPCR"="grey","Defense"="grey","Cytoskeleton"="grey","Cell wall misc"="grey",
                 "Carbohydrate storage"="grey","Cell wall biosynthesis "="grey")
)
#function to reorder clusters
callback = function(hc, mat){
    sv = svd(t(mat))$v[,1]
    dend = reorder(as.dendrogram(hc), wts = sv)
    as.hclust(dend)
}

png("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_multi_dge_division.png",res=300,width=2000,height=1000)
plot_transcript_heatmap(so, transcripts=mult_sig$target_id[mult_sig$change!="low_logFC"],
                        cluster_transcripts=T,show_rownames=F,
                        annotation_row=annotation_vector,clustering_callback = callback,
                        annotation_colors = ann_colors,fontsize=7)
dev.off()

## pdf 
##   4

knitr::include_graphics("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_multi_dge_division.png") 

* Look at boxplots for Cell division

cell_division_list<-annotation %>% filter(Function=="Cell division, proliferation and growth") %>% row.names()
cell_division_table<-mult_sig %>% filter(target_id %in% cell_division_list) %>% arrange(b)

plot_bootstrap(so, 
               target_id = cell_division_table$target_id[1], 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = cell_division_table$target_id[2], 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = cell_division_table$target_id[3], 
               units = "est_counts", 
               color_by = "condition")

• Highlighting TFs
  • In total, in the genome we have 393 putative TFs
  • Of them, 25 are from lichen-enriched orthoproups

ann_colors = list(
    condition = c("lichen_thallus"="#F8766D","xanthoria_culture"="#619CFF"),
    Function = c("Transcription factors"=brewer.pal(n = 8, name = "Dark2")[1],
                 "Transporters"="grey",
                 "Protein ubiquitination"="grey",
                 "Cell division, proliferation and growth"="grey",
                 "Acetyl-CoA production and metabolism"="grey",
                 "Cell surface and cell wall proteins"="grey",
                 "Cell wall remodeling"="grey",
                 "Velvet"="grey","Stress response genes"="grey","RNA interference"="grey",
                 "RNA binding proteins"="grey","Ribosomal genes"="grey","Oxylipins"="grey",
                 "MAPK signaling pathway"="grey","Lipid metabolism"="grey","G-proteins and GPCR"="grey","Defense"="grey","Cytoskeleton"="grey","Cell wall misc"="grey",
                 "Carbohydrate storage"="grey","Cell wall biosynthesis "="grey")
)

png("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_multi_dge_TFs.png",res=300,width=2000,height=1000)
plot_transcript_heatmap(so, transcripts=mult_sig$target_id[mult_sig$change!="low_logFC"],
                        cluster_transcripts=T,show_rownames=F,
                        annotation_row=annotation_vector,clustering_callback = callback,
                        annotation_colors = ann_colors,fontsize=7)
dev.off()

## pdf 
##   4

knitr::include_graphics("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_multi_dge_TFs.png") 

• Highlighting transporters
  • In total, in the genome we have 229 putative transporters
  • Of them, 44 are from lichen-enriched orthoproups

ann_colors = list(
    condition = c("lichen_thallus"="#F8766D","xanthoria_culture"="#619CFF"),
    Function = c("Transcription factors"="grey",
                 "Transporters"=brewer.pal(n = 8, name = "Dark2")[2],
                 "Protein ubiquitination"="grey",
                 "Cell division, proliferation and growth"="grey",
                 "Acetyl-CoA production and metabolism"="grey",
                 "Cell surface and cell wall proteins"="grey",
                 "Cell wall remodeling"="grey",
                 "Velvet"="grey","Stress response genes"="grey","RNA interference"="grey",
                 "RNA binding proteins"="grey","Ribosomal genes"="grey","Oxylipins"="grey",
                 "MAPK signaling pathway"="grey","Lipid metabolism"="grey","G-proteins and GPCR"="grey","Defense"="grey","Cytoskeleton"="grey","Cell wall misc"="grey",
                 "Carbohydrate storage"="grey","Cell wall biosynthesis "="grey")
)
#function to reorder clusters
callback = function(hc, mat){
    sv = svd(t(mat))$v[,1]
    dend = reorder(as.dendrogram(hc), wts = sv)
    as.hclust(dend)
}
png("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_multi_dge_transporters.png",res=300,width=2000,height=1000)
plot_transcript_heatmap(so, transcripts=mult_sig$target_id[mult_sig$change!="low_logFC"],
                        cluster_transcripts=T,show_rownames=F,
                        annotation_row=annotation_vector,clustering_callback = callback,
                        annotation_colors = ann_colors,fontsize=7)
dev.off()

## pdf 
##   4

knitr::include_graphics("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_multi_dge_transporters.png") 

• Highlighting cell wall proteins

ann_colors = list(
    condition = c("lichen_thallus"="#F8766D","xanthoria_culture"="#619CFF"),
    Function = c("Transcription factors"="grey",
                 "Transporters"="grey",
                 "Cell surface and cell wall proteins"=brewer.pal(n = 8, name = "Dark2")[3],
                 "Cell wall remodeling"=brewer.pal(n = 8, name = "Dark2")[5],
                 "Cell wall misc"=brewer.pal(n = 8, name = "Dark2")[6],
                 "Cell wall biosynthesis "=brewer.pal(n = 8, name = "Dark2")[7],
                 "Protein ubiquitination"="grey",
                 "Cell division, proliferation and growth"="grey",
                 "Acetyl-CoA production and metabolism"="grey",
                 "Velvet"="grey","Stress response genes"="grey","RNA interference"="grey",
                 "RNA binding proteins"="grey","Ribosomal genes"="grey","Oxylipins"="grey",
                 "MAPK signaling pathway"="grey","Lipid metabolism"="grey","G-proteins and GPCR"="grey","Defense"="grey","Cytoskeleton"="grey",
                 "Carbohydrate storage"="grey")
)

png("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_multi_dge_cell_wass.png",res=300,width=2000,height=1000)
plot_transcript_heatmap(so, transcripts=mult_sig$target_id[mult_sig$change!="low_logFC"],
                        cluster_transcripts=T,show_rownames=F,
                        annotation_row=annotation_vector,clustering_callback = callback,
                        annotation_colors = ann_colors,fontsize=7)
dev.off()

## pdf 
##   4

knitr::include_graphics("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_multi_dge_cell_wass.png") 

• Redraw the heatmap manually (since plot_transcript_heatmpap() is not very flexible)
  • For this, I tool the source code from sleuth and modified it
  • Used log transformation and offset = 1, following the default parameters in plot_transcript_heatmpap()

library(ComplexHeatmap)
library(viridis)
#make a matrix
tabd_df <- so$obs_norm[so$obs_norm$target_id %in% target_id,]
tabd_df <- dplyr::select(tabd_df, target_id, sample, 
            tpm)
tabd_df <- reshape2::dcast(tabd_df, target_id ~ sample, 
            value.var = "tpm") 
rownames(tabd_df) <- tabd_df$target_id
tabd_df$target_id <- NULL
trans_mat <- as.matrix(log(tabd_df + 1))

#filter to include only DGE and multicellularity-related
include_list<-mult_sig$target_id[mult_sig$change %in% c("lichen","culture")]
filt_mat<-subset(trans_mat, rownames(trans_mat) %in% include_list)

#define column annotations
s2c <- so$sample_to_covariates
s2c<-data.frame("sample"=colnames(filt_mat)) %>% left_join(s2c)
rownames(s2c)<-s2c$sample
s2c<-s2c %>% select(condition)
s2c$condition[s2c$condition=="xanthoria_culture"]<-"Main Fungus culture"
s2c$condition[s2c$condition=="lichen_thallus"]<-"Lichen Thallus"
ta_colors = c("Main Fungus culture" = "#619CFF", "Lichen Thallus" = "#F8766D")
ta = HeatmapAnnotation(df=s2c,col = list(condition = ta_colors))

#define row annotation
g2r<-data.frame("TranscriptID"=rownames(filt_mat)) %>% left_join(annotation) %>%
  select(Function)
la = rowAnnotation(df = g2r)

#plot
HM = Heatmap(filt_mat, show_row_names = F, show_column_names = T, name = " ",
            top_annotation = ta, 
            left_annotation = la,
            col=viridis(100) )
HM

4.4. Genes from lichen-enriched orthogroups

• The list of lichen-enriched orthogroups, see ../02_mycobiont_genome/notebook/09_lichen_specific_genes.html
• Heatmap showing all 1226 lichen-specific genes, regardles of DGE status

funannot2<-read.delim2("../../02_mycobiont_genome/analysis_and_temp_files/09_ortho/lichen_enriched_ortho_in_xanpa.tsv",sep="\t")
png("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_lichen_enriched_all.png",res=300,width=2000,height=1500)
plot_transcript_heatmap(so, transcripts=funannot2$TranscriptID[funannot2$lichen_ortho==T],
                        cluster_transcripts=T,show_rownames=F,
                        clustering_callback = callback)
dev.off()

## pdf 
##   4

knitr::include_graphics("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_lichen_enriched_all.png") 

• Of them, 361 are differentially expressed. This is 29.5% (compared to 15.6370139% across the genome)

og_sig<-sig %>% filter(target_id %in% funannot2$TranscriptID[funannot2$lichen_ortho==T])
og_sig %>% group_by(change) %>% summarise(n=n())

## # A tibble: 3 × 2
##   change        n
##   <chr>     <int>
## 1 culture      97
## 2 lichen      264
## 3 low_logFC   374

• Heatmap with only DGE genes. Lichen samples are split based on substrates

png("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_lichen_enriched_dge.png",res=300,width=2000,height=1000)
plot_transcript_heatmap(so, transcripts=og_sig$target_id[og_sig$change!="low_logFC"],
                        cluster_transcripts=T,show_rownames=F,
                        clustering_callback = callback)
dev.off()

## pdf 
##   4

knitr::include_graphics("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_lichen_enriched_dge.png") 

• Of 361 DGE lichen-specific genes, 168 have no functional annotation. This is 47%, compared to 0.3081806) across the whole genome

4.5. Secondary metabolism clusters

• How many genes are in the genome in total that are annotated as part of a SM gene cluster? 1239 in 59 clusters
  • NB: this is according to funannotate indexing. The number of regions displayed in the antiSMASH output is 49, since funannotate have split some of the ‘mixed’ clusters in to several)
  • Funannotate indexing here is misleading, because it didn’t handle correctly cases in which one gene is assigned to different clusters. I manually compiled a table instead

funannot2 %>% group_by(antiSMASH,Contig) %>% summarize(n=n()) %>% filter(!is.na(antiSMASH))

## `summarise()` has grouped output by 'antiSMASH'. You can override using the
## `.groups` argument.

## # A tibble: 59 × 3
## # Groups:   antiSMASH [7]
##    antiSMASH Contig            n
##    <chr>     <chr>         <int>
##  1 Cluster_1 Xp_GTX0501_1     39
##  2 Cluster_1 Xp_GTX0501_10    20
##  3 Cluster_1 Xp_GTX0501_11    15
##  4 Cluster_1 Xp_GTX0501_12    12
##  5 Cluster_1 Xp_GTX0501_13    24
##  6 Cluster_1 Xp_GTX0501_14    11
##  7 Cluster_1 Xp_GTX0501_15    18
##  8 Cluster_1 Xp_GTX0501_17    24
##  9 Cluster_1 Xp_GTX0501_2     41
## 10 Cluster_1 Xp_GTX0501_24    44
## # ℹ 49 more rows

• Save SM-related genes as a list

sm_genes<-funannot2 %>% filter(!is.na(antiSMASH)) %>% mutate(cluster = paste0(Contig,"_",antiSMASH)) %>% select(-c(gDNA,mRNA,CDS.transcript,Translation,CAZyme,COG,EggNog,GO.Terms,InterPro,PFAM,Protease,Secreted))

• 318 of them are differentially expressed. Weirdly enough, 30% of thouse are upregulated in culture!

sm_sig<-sig %>% filter(target_id %in% sm_genes$TranscriptID)
sm_sig %>% group_by(change) %>% summarise(n=n())

## # A tibble: 3 × 2
##   change        n
##   <chr>     <int>
## 1 culture      96
## 2 lichen      222
## 3 low_logFC   379

• Heatmap of those

png("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_SM_dge.png",res=300,width=2000,height=1000)
plot_transcript_heatmap(so, transcripts=sm_sig$target_id[sm_sig$change!="low_logFC"],
                        cluster_transcripts=T,show_rownames=F,
                        clustering_callback = callback)
dev.off()

## pdf 
##   4

knitr::include_graphics("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_SM_dge.png") 

• Break down by cluster

library(splitstackshape)
antismash<-read.delim2("../../02_mycobiont_genome/analysis_and_temp_files/06_annotate_lecanoro/GTX0501_pred/antismash/antismash_summary.txt")

#get a list of all genes in each cluster
antismash_gene_all<-antismash %>% mutate(start_num=as.numeric(gsub("^.*?_","",Start)),
                                         end_num=as.numeric(gsub("^.*?_","",End))) %>%
  mutate(gene_number=end_num-start_num+1) %>%
  expandRows("gene_number", drop = FALSE) %>%
  group_by(start_num,end_num) %>%
  mutate(gene_num = seq(start_num[1],end_num[1],by = 1)) %>%
  mutate(GeneID=ifelse(gene_num<1000,paste0("XANPAGTX0501_000",gene_num),
                                            ifelse(gene_num<10000,paste0("XANPAGTX0501_00",gene_num),
                                            paste0("XANPAGTX0501_0",gene_num)))) %>%
  mutate(Core_gene = ifelse(GeneID==Core_gene1|GeneID==Core_gene2,T,F)) %>% ungroup %>%
  select(GeneID,Cluster,Description,Core_gene)

#add transcriptomic results
summary_antismash_all<-antismash_gene_all %>% left_join(funannot2,relationship = "many-to-many") %>% 
  left_join(sig, by = c("TranscriptID"="target_id")) %>%
  group_by(Cluster,change) %>% summarize(n=n()) %>% 
  pivot_wider(names_from=change,values_from=n,values_fill=0) %>%
  left_join(antismash)

## Joining with `by = join_by(GeneID)`
## `summarise()` has grouped output by 'Cluster'. You can override using the
## `.groups` argument.
## Joining with `by = join_by(Cluster)`

• Looking at just core biosynthetic genes, weirdly some of them are upregulated in culture

summary_antismash_core<-antismash_gene_all %>% filter(Core_gene==T) %>%
  left_join(funannot2,relationship = "many-to-many") %>% 
  left_join(sig, by = c("TranscriptID"="target_id")) %>%
  mutate(change=ifelse(change %in% c("lichen","culture"),change,"Non-DGE")) %>%
  group_by(Cluster) %>% mutate(Core_gene_status=paste(change,collapse=",")) %>%
  select(Cluster,Core_gene_status) %>% distinct()

## Joining with `by = join_by(GeneID)`

summary_antismash_core %>% group_by(Core_gene_status) %>%summarize(n=n())

## # A tibble: 6 × 2
##   Core_gene_status     n
##   <chr>            <int>
## 1 Non-DGE             35
## 2 Non-DGE,Non-DGE      2
## 3 culture              6
## 4 culture,culture      1
## 5 lichen              14
## 6 lichen,Non-DGE       1

• In most clusters, the mojority is non DGE, as expected. Otherwise, the results are unexpectedly mixed.
  • 6 clusters are definitiely upregulated in lichen (core gene is upregulated in lichen, and no genes are upregulated in culture)
  • One is clearly upregulated in culture! Xp_GTX0501_8_Cluster_1 (unknown NRPS)
  • The rest is mixed

summary_antismash_all<-summary_antismash_all %>% left_join(summary_antismash_core)

## Joining with `by = join_by(Cluster)`

summary_antismash_all %>%
  kable(format = "html", col.names = colnames(summary_antismash_all)) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

Cluster	culture	lichen	low_logFC	NA	Description	Start	End	Core_gene1	Core_gene2	KnownClusterBlast_MIBIG	KnownClusterBlast_description	KnownClusterBlast_Similarity	KnownClusterBlast_includes_core	Core_gene_status
Xp_GTX0501_10_Cluster_1	2	12	4	2	NRPS-like	XANPAGTX0501_006291	XANPAGTX0501_006310	XANPAGTX0501_006297					NA	Non-DGE
Xp_GTX0501_10_Cluster_2	2	9	6	8	T1PKS	XANPAGTX0501_006308	XANPAGTX0501_006332	XANPAGTX0501_006319		BGC0002215	HEx-pks23 polyketide<ca>	0.22	1	lichen
Xp_GTX0501_10_Cluster_3	0	2	14	11	NRPS-like	XANPAGTX0501_006344	XANPAGTX0501_006369	XANPAGTX0501_006358					NA	Non-DGE
Xp_GTX0501_10_Cluster_4	2	1	14	9	T3PKS	XANPAGTX0501_006734	XANPAGTX0501_006757	XANPAGTX0501_006744					NA	Non-DGE
Xp_GTX0501_11_Cluster_1	3	2	2	7	NRPS	XANPAGTX0501_006840	XANPAGTX0501_006853	XANPAGTX0501_006845		BGC0002235	ACE1	0.11	1	lichen
Xp_GTX0501_12_Cluster_1	1	4	2	5	T1PKS	XANPAGTX0501_007263	XANPAGTX0501_007274	XANPAGTX0501_007266		BGC0000146	solanapyrone D	0.33	1	Non-DGE
Xp_GTX0501_12_Cluster_2	0	9	12	11	T1PKS	XANPAGTX0501_007334	XANPAGTX0501_007363	XANPAGTX0501_007346					NA	Non-DGE,Non-DGE
Xp_GTX0501_12_Cluster_3	3	1	4	5	terpene	XANPAGTX0501_007388	XANPAGTX0501_007400	XANPAGTX0501_007395					NA	Non-DGE
Xp_GTX0501_13_Cluster_1	1	5	2	14	NRPS-like	XANPAGTX0501_007869	XANPAGTX0501_007889	XANPAGTX0501_007880					NA	Non-DGE
Xp_GTX0501_14_Cluster_1	1	2	4	3	terpene	XANPAGTX0501_007984	XANPAGTX0501_007993	XANPAGTX0501_007988					NA	Non-DGE
Xp_GTX0501_15_Cluster_1	1	7	8	3	NRPS-like	XANPAGTX0501_008267	XANPAGTX0501_008284	XANPAGTX0501_008272					NA	lichen
Xp_GTX0501_17_Cluster_1	0	7	8	7	T1PKS	XANPAGTX0501_008845	XANPAGTX0501_008866	XANPAGTX0501_008852		BGC0000156	TAN-1612 biosynthetic gene cluster fromAspergillus niger	0.6	1	lichen
Xp_GTX0501_1_Cluster_1	5	6	12	15	fungal-RiPP-like	XANPAGTX0501_000667	XANPAGTX0501_000702	XANPAGTX0501_000685					NA	lichen
Xp_GTX0501_1_Cluster_2	1	7	4	14	T1PKS	XANPAGTX0501_000912	XANPAGTX0501_000937	XANPAGTX0501_000926		BGC0000146	solanapyrone D	0.5	0	Non-DGE
Xp_GTX0501_24_Cluster_1	10	10	7	17	fungal-RiPP-like	XANPAGTX0501_009693	XANPAGTX0501_009736	XANPAGTX0501_009715	XANPAGTX0501_009716				NA	culture,culture
Xp_GTX0501_25_Cluster_1	0	2	4	11	terpene	XANPAGTX0501_009858	XANPAGTX0501_009874	XANPAGTX0501_009866					NA	Non-DGE
Xp_GTX0501_27_Cluster_1	1	2	12	7	NRPS-like	XANPAGTX0501_009956	XANPAGTX0501_009977	XANPAGTX0501_009964					NA	Non-DGE
Xp_GTX0501_2_Cluster_1	2	6	15	16	fungal-RiPP-like	XANPAGTX0501_001046	XANPAGTX0501_001083	XANPAGTX0501_001064					NA	lichen
Xp_GTX0501_2_Cluster_2	1	3	10	14	NRPS	XANPAGTX0501_001225	XANPAGTX0501_001250	XANPAGTX0501_001239					NA	Non-DGE
Xp_GTX0501_2_Cluster_3	1	1	8	14	NRPS-like	XANPAGTX0501_001291	XANPAGTX0501_001314	XANPAGTX0501_001305					NA	Non-DGE
Xp_GTX0501_2_Cluster_4	0	0	7	6	terpene	XANPAGTX0501_001616	XANPAGTX0501_001628	XANPAGTX0501_001622					NA	Non-DGE
Xp_GTX0501_2_Cluster_5	0	2	3	18	T1PKS	XANPAGTX0501_001669	XANPAGTX0501_001691	XANPAGTX0501_001679					NA	Non-DGE
Xp_GTX0501_2_Cluster_6	0	0	5	19	NRP-metallophore	XANPAGTX0501_001682	XANPAGTX0501_001705	XANPAGTX0501_001696	XANPAGTX0501_001694				NA	Non-DGE,Non-DGE
Xp_GTX0501_2_Cluster_7	0	0	5	16	NRPS	XANPAGTX0501_001682	XANPAGTX0501_001702	XANPAGTX0501_001694					NA	Non-DGE
Xp_GTX0501_35_Cluster_1	6	3	3	9	NRPS-like	XANPAGTX0501_010404	XANPAGTX0501_010423	XANPAGTX0501_010409					NA	culture
Xp_GTX0501_35_Cluster_2	2	8	4	9	T1PKS	XANPAGTX0501_010418	XANPAGTX0501_010440	XANPAGTX0501_010430					NA	lichen
Xp_GTX0501_36_Cluster_1	2	4	9	11	T1PKS	XANPAGTX0501_010449	XANPAGTX0501_010474	XANPAGTX0501_010464		BGC0001242	oxyjavanicin	0.25	1	Non-DGE
Xp_GTX0501_3_Cluster_1	10	8	0	3	NRPS	XANPAGTX0501_001961	XANPAGTX0501_001981	XANPAGTX0501_001972		BGC0001741	phyllostictine A/phyllostictine B	0.5	1	culture
Xp_GTX0501_3_Cluster_2	10	6	0	4	T1PKS	XANPAGTX0501_001963	XANPAGTX0501_001982	XANPAGTX0501_001973		BGC0001741	phyllostictine A/phyllostictine B	0.5	1	culture
Xp_GTX0501_3_Cluster_3	0	7	1	6	terpene	XANPAGTX0501_002180	XANPAGTX0501_002193	XANPAGTX0501_002188					NA	Non-DGE
Xp_GTX0501_41_Cluster_1	0	1	9	3	NRPS-like	XANPAGTX0501_010609	XANPAGTX0501_010621	XANPAGTX0501_010621					NA	lichen
Xp_GTX0501_43_Cluster_1	0	4	4	16	T1PKS	XANPAGTX0501_010622	XANPAGTX0501_010644	XANPAGTX0501_010632					NA	Non-DGE
Xp_GTX0501_48_Cluster_1	3	6	2	8	NRPS-like	XANPAGTX0501_010686	XANPAGTX0501_010704	XANPAGTX0501_010692					NA	culture
Xp_GTX0501_4_Cluster_1	1	0	3	9	terpene	XANPAGTX0501_002454	XANPAGTX0501_002466	XANPAGTX0501_002460					NA	Non-DGE
Xp_GTX0501_4_Cluster_2	0	6	15	12	NRPS-like	XANPAGTX0501_002475	XANPAGTX0501_002501	XANPAGTX0501_002488					NA	lichen
Xp_GTX0501_4_Cluster_3	0	1	6	7	terpene	XANPAGTX0501_002520	XANPAGTX0501_002531	XANPAGTX0501_002527		BGC0001839	squalestatin S1	0.4	1	Non-DGE
Xp_GTX0501_4_Cluster_4	0	3	10	13	NRPS	XANPAGTX0501_002525	XANPAGTX0501_002549	XANPAGTX0501_002535		BGC0002164	peramine	1	1	lichen
Xp_GTX0501_4_Cluster_5	0	3	5	17	NRPS	XANPAGTX0501_003108	XANPAGTX0501_003131	XANPAGTX0501_003119					NA	lichen
Xp_GTX0501_50_Cluster_1	0	2	1	3	T1PKS	XANPAGTX0501_010705	XANPAGTX0501_010710	XANPAGTX0501_010709		BGC0000146	solanapyrone D	0.33	1	Non-DGE
Xp_GTX0501_52_Cluster_1	2	3	1	2	NRPS	XANPAGTX0501_010711	XANPAGTX0501_010717	XANPAGTX0501_010715					NA	Non-DGE
Xp_GTX0501_5_Cluster_1	4	5	2	9	T1PKS	XANPAGTX0501_003170	XANPAGTX0501_003189	XANPAGTX0501_003176		BGC0002515	solanapyrone A	0.4	1	culture
Xp_GTX0501_5_Cluster_2	7	5	7	7	T1PKS	XANPAGTX0501_003179	XANPAGTX0501_003204	XANPAGTX0501_003194					NA	Non-DGE
Xp_GTX0501_5_Cluster_3	0	3	7	16	NRPS,T1PKS	XANPAGTX0501_003287	XANPAGTX0501_003311	XANPAGTX0501_003300		BGC0001067	fumagillin/_-trans-bergamotene/fumagillol	0.2	0	Non-DGE
Xp_GTX0501_5_Cluster_4	2	2	11	13	NRPS-like	XANPAGTX0501_003361	XANPAGTX0501_003388	XANPAGTX0501_003374					NA	lichen
Xp_GTX0501_6_Cluster_1	0	3	10	10	T1PKS	XANPAGTX0501_004370	XANPAGTX0501_004390	XANPAGTX0501_004380					NA	Non-DGE
Xp_GTX0501_6_Cluster_2	0	4	7	13	T1PKS	XANPAGTX0501_004397	XANPAGTX0501_004420	XANPAGTX0501_004410					NA	Non-DGE
Xp_GTX0501_7_Cluster_1	0	4	10	12	T1PKS	XANPAGTX0501_004611	XANPAGTX0501_004634	XANPAGTX0501_004622		BGC0001258	1,3,6,8-tetrahydroxynaphthalene	1	1	Non-DGE
Xp_GTX0501_7_Cluster_2	0	2	7	3	terpene	XANPAGTX0501_004765	XANPAGTX0501_004776	XANPAGTX0501_004770					NA	lichen
Xp_GTX0501_7_Cluster_3	1	9	9	13	T1PKS	XANPAGTX0501_005055	XANPAGTX0501_005086	XANPAGTX0501_005070					NA	Non-DGE
Xp_GTX0501_7_Cluster_4	1	7	7	10	NRPS-like	XANPAGTX0501_005071	XANPAGTX0501_005095	XANPAGTX0501_005087					NA	Non-DGE
Xp_GTX0501_7_Cluster_5	1	8	7	8	T1PKS	XANPAGTX0501_005075	XANPAGTX0501_005098	XANPAGTX0501_005090					NA	Non-DGE
Xp_GTX0501_8_Cluster_1	9	0	4	11	NRPS	XANPAGTX0501_005105	XANPAGTX0501_005128	XANPAGTX0501_005116					NA	culture
Xp_GTX0501_8_Cluster_2	1	6	9	13	T1PKS	XANPAGTX0501_005240	XANPAGTX0501_005265	XANPAGTX0501_005252					NA	lichen
Xp_GTX0501_8_Cluster_3	1	5	10	13	T1PKS	XANPAGTX0501_005280	XANPAGTX0501_005306	XANPAGTX0501_005291		BGC0000046	depudecin	0.33	0	Non-DGE
Xp_GTX0501_8_Cluster_4	5	4	11	15	fungal-RiPP-like	XANPAGTX0501_005329	XANPAGTX0501_005361	XANPAGTX0501_005349					NA	Non-DGE
Xp_GTX0501_8_Cluster_5	1	3	4	5	terpene	XANPAGTX0501_005377	XANPAGTX0501_005388	XANPAGTX0501_005382					NA	lichen,Non-DGE
Xp_GTX0501_9_Cluster_1	0	4	3	14	T1PKS	XANPAGTX0501_005732	XANPAGTX0501_005752	XANPAGTX0501_005742		BGC0001258	1,3,6,8-tetrahydroxynaphthalene	1	1	Non-DGE
Xp_GTX0501_9_Cluster_2	2	0	5	16	NRPS	XANPAGTX0501_005742	XANPAGTX0501_005764	XANPAGTX0501_005751					NA	Non-DGE
Xp_GTX0501_9_Cluster_3	2	3	12	11	T1PKS	XANPAGTX0501_005922	XANPAGTX0501_005948	XANPAGTX0501_005935		BGC0002194	epipyrone A	0.75	1	Non-DGE

• The list of definitiely upregulated in lichen
  • 2 of them have mathces to known clusters and are discussed below

summary_antismash_all %>% filter(culture==0,lichen>0,grepl("lichen",Core_gene_status))  %>% 
  kable(format = "html", col.names = colnames(summary_antismash_all)) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

Cluster	culture	lichen	low_logFC	NA	Description	Start	End	Core_gene1	Core_gene2	KnownClusterBlast_MIBIG	KnownClusterBlast_description	KnownClusterBlast_Similarity	KnownClusterBlast_includes_core	Core_gene_status
Xp_GTX0501_17_Cluster_1	0	7	8	7	T1PKS	XANPAGTX0501_008845	XANPAGTX0501_008866	XANPAGTX0501_008852		BGC0000156	TAN-1612 biosynthetic gene cluster fromAspergillus niger	0.6	1	lichen
Xp_GTX0501_41_Cluster_1	0	1	9	3	NRPS-like	XANPAGTX0501_010609	XANPAGTX0501_010621	XANPAGTX0501_010621					NA	lichen
Xp_GTX0501_4_Cluster_2	0	6	15	12	NRPS-like	XANPAGTX0501_002475	XANPAGTX0501_002501	XANPAGTX0501_002488					NA	lichen
Xp_GTX0501_4_Cluster_4	0	3	10	13	NRPS	XANPAGTX0501_002525	XANPAGTX0501_002549	XANPAGTX0501_002535		BGC0002164	peramine	1	1	lichen
Xp_GTX0501_4_Cluster_5	0	3	5	17	NRPS	XANPAGTX0501_003108	XANPAGTX0501_003131	XANPAGTX0501_003119					NA	lichen
Xp_GTX0501_7_Cluster_2	0	2	7	3	terpene	XANPAGTX0501_004765	XANPAGTX0501_004776	XANPAGTX0501_004770					NA	lichen

Parietin cluster

• Cross-referencing with Theo Llewellyn’s paper. In his analysis of many lecanoromycete genomes, he identified putative anthraquinone BGC as those similar to 4 MIBiG clusters:
  • the anthraquinones emodin in Escovopsis weberi
  • asperthecin in Aspergillus nidulans FGSC A4
  • endocrocin/clavorubin in Claviceps purpurea
  • the structurally related alternariol in Aspergillus nidulans FGSC A4 and TAN-1612 Aspergillus niger
• Our genome has one such cluster: Xp_GTX0501_17_Cluster_1 is a TPK1S cluster similar to TAN-1612
• This cluster is one of the 6 definitely upregulated in lichen
• This matches Theo’s results, since he also shown one such cluster in the X. parietina from JGI
• Also the structure of the gene cluster matches what Theo describes as a conserved 4-gene structure unique to Teloschistales:
  • FUN_008850: a transporter with an ABC-casset (IPR003439 ABC transporter-like, ATP-binding domain); - strand
  • FUN_008851: metallo-beta-lactamase-type thioesterase (IPR001279 Metallo-beta-lactamase)
  • FUN_008852: PKS-synthase with SAT-KS-AT-PT-ACP domains (starter unit acyltransferase domain - ketoacyl synthase - acyltransferase - product template - acyl carrier protein)
  • FUN_008853: a dehydratase with a single EthylD domain (IPR009799 EthD domain)
• None of other PKS clusters had this structure
• All four of the genes are upregulated in lichen

sig %>% filter(target_id %in% c("XANPAGTX0501_008850-T1","XANPAGTX0501_008851-T1","XANPAGTX0501_008852-T1","XANPAGTX0501_008853-T1")) %>% select(target_id,qval,b,change)

## # A tibble: 4 × 4
##   target_id                  qval     b change
##   <chr>                     <dbl> <dbl> <chr> 
## 1 XANPAGTX0501_008850-T1 6.06e-22 -1.70 lichen
## 2 XANPAGTX0501_008851-T1 5.87e-21 -1.93 lichen
## 3 XANPAGTX0501_008852-T1 1.87e-22 -2.08 lichen
## 4 XANPAGTX0501_008853-T1 3.26e-69 -4.00 lichen

• Boxplots show clearly that it is upregulated in lichen

plot_bootstrap(so, 
               target_id = "XANPAGTX0501_008850-T1", 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = "XANPAGTX0501_008851-T1", 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = "XANPAGTX0501_008852-T1", 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = "XANPAGTX0501_008853-T1", 
               units = "est_counts", 
               color_by = "condition")

Peramine-like cluster

• Main biosynthetic gene from Xp_GTX0501_4_Cluster_4 (XANPAGTX0501_002535) is 65% identical to peramine synthase (evalue=0.0). However, it’s much shorter than the reference (1425 aa vs 2773 aa in the reference)
• This gene is from a lichen-enriched orthogroup
• Peramine is an anti-insect alcaloid from Epichloe, which is a mutualistic endophyte. Thought to be offer the host plant protection from herbivory
• Some lichen compaunds are apparently alkaloids, including rhizocarpic acid, but none of these are known from Xanthoria. There is one report showing trace amounts of alkaloids in Xanthoria
• This paper describes similar cluster from Cladonia grayi
• They also report similar cluster from Xanthoria parietina, but deem it non-functional or producing something other than peramine. The reason for that is two missing domains: A1 (first of the adenylylation domains; peramine synthase from Cladonia has two of them, while Xanthoria only one) and R (reductase domain). In total, their annotation has 3 domains:
  • C (condensation domain)
  • A (adenylylation domain)
  • M (methylation domain)
• According to antiSMASH, our putative peramine synthase has four domains. First three are the same as in the paper, but the last (CP or PCP) is an addition
  • C (condensation domain)
  • A (adenylylation domain)
  • nMT (nitrogen methyltransferase)
  • CP (peptidyl-carrier protein domain)
• I ran antiSMASH on Cladonia grayi to compare. There, putative peramine synthase has 6 domains: A, CP, C, nMT, CP, NAD. The length of the Cladonia protein is close to that of the reference
• Conclusion: this cluster is likely functional, but producing something other than peramine

4.6. Protein Kinases

• In total, the genome has 144 proteins with a protein kinase domain. Of them, 24 are from lichen-enriched orthogroups

funannot2 %>% filter(grepl("IPR000719",InterPro)) %>% group_by(lichen_ortho) %>% summarize(n=n())

## # A tibble: 2 × 2
##   lichen_ortho     n
##   <lgl>        <int>
## 1 FALSE          115
## 2 TRUE            19

• Lichen and culture have similar number of kinases upregulated

funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>%
  filter(grepl("IPR000719",InterPro)) %>% group_by(change) %>% summarize(n=n())

## # A tibble: 4 × 2
##   change        n
##   <chr>     <int>
## 1 culture      11
## 2 lichen       10
## 3 low_logFC    53
## 4 <NA>         60

• How many of them are serine/threonine kinases? In culture 9 (out of 11) upregulated kinases are serine/threonine kinases, in lichens it’s only 4

funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>%
  filter(grepl("IPR008271",InterPro)) %>% group_by(change) %>% summarize(n=n())

## # A tibble: 4 × 2
##   change        n
##   <chr>     <int>
## 1 culture       9
## 2 lichen        4
## 3 low_logFC    42
## 4 <NA>         47

• List them. The list includes one lichen-upregulated “MAP kinase-activated protein kinase”

funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>%
  filter(grepl("IPR008271",InterPro),change %in% c("culture","lichen")) %>%
  select(TranscriptID,b,change,Product,InterPro) %>%
  kable(format = "html", col.names = c("TranscriptID","b","change","Product","InterPro")) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

TranscriptID	b	change	Product	InterPro
XANPAGTX0501_000131-T1	3.173122	culture	hypothetical protein	IPR000719 Protein kinase domain;IPR008271 Serine/threonine-protein kinase, active site;IPR011009 Protein kinase-like domain superfamily;IPR011990 Tetratricopeptide-like helical domain superfamily;IPR017441 Protein kinase, ATP binding site
XANPAGTX0501_002130-T1	1.107301	culture	hypothetical protein	IPR000719 Protein kinase domain;IPR001245 Serine-threonine/tyrosine-protein kinase, catalytic domain;IPR002110 Ankyrin repeat;IPR006597 Sel1-like repeat;IPR008271 Serine/threonine-protein kinase, active site;IPR011009 Protein kinase-like domain superfamily;IPR011990 Tetratricopeptide-like helical domain superfamily;IPR020683 Domain of unknown function DUF3447;IPR036770 Ankyrin repeat-containing domain superfamily
XANPAGTX0501_002999-T3	1.110073	culture	Serine/threonine-protein kinase, variant 3	IPR000008 C2 domain;IPR000719 Protein kinase domain;IPR000961 AGC-kinase, C-terminal;IPR008271 Serine/threonine-protein kinase, active site;IPR011009 Protein kinase-like domain superfamily;IPR017441 Protein kinase, ATP binding site;IPR017892 Protein kinase, C-terminal;IPR035892 C2 domain superfamily
XANPAGTX0501_003063-T3	1.307124	culture	Cytochrome c oxidase subunit 1, variant 3	IPR000719 Protein kinase domain;IPR008271 Serine/threonine-protein kinase, active site;IPR011009 Protein kinase-like domain superfamily;IPR017441 Protein kinase, ATP binding site
XANPAGTX0501_003150-T1	1.034833	culture	hypothetical protein	IPR000719 Protein kinase domain;IPR008271 Serine/threonine-protein kinase, active site;IPR011009 Protein kinase-like domain superfamily
XANPAGTX0501_003466-T1	-1.376968	lichen	hypothetical protein	IPR000719 Protein kinase domain;IPR008271 Serine/threonine-protein kinase, active site;IPR011009 Protein kinase-like domain superfamily
XANPAGTX0501_003979-T1	1.608051	culture	Serine/threonine protein kinase	IPR000719 Protein kinase domain;IPR008271 Serine/threonine-protein kinase, active site;IPR011009 Protein kinase-like domain superfamily;IPR017441 Protein kinase, ATP binding site
XANPAGTX0501_004521-T1	-1.452240	lichen	hypothetical protein	IPR008271 Serine/threonine-protein kinase, active site;IPR011009 Protein kinase-like domain superfamily
XANPAGTX0501_004525-T1	-1.003000	lichen	hypothetical protein	IPR000719 Protein kinase domain;IPR008271 Serine/threonine-protein kinase, active site;IPR011009 Protein kinase-like domain superfamily
XANPAGTX0501_005890-T1	1.279397	culture	hypothetical protein	IPR000719 Protein kinase domain;IPR002110 Ankyrin repeat;IPR008271 Serine/threonine-protein kinase, active site;IPR011009 Protein kinase-like domain superfamily;IPR020683 Domain of unknown function DUF3447;IPR036770 Ankyrin repeat-containing domain superfamily
XANPAGTX0501_006750-T1	1.049144	culture	hypothetical protein	IPR000719 Protein kinase domain;IPR008271 Serine/threonine-protein kinase, active site;IPR011009 Protein kinase-like domain superfamily
XANPAGTX0501_007777-T2	1.360843	culture	eukaryotic translation initiation factor 2-alpha kinase	IPR000719 Protein kinase domain;IPR008271 Serine/threonine-protein kinase, active site;IPR011009 Protein kinase-like domain superfamily;IPR016255 eIF-2-alpha kinase Gcn2;IPR017441 Protein kinase, ATP binding site;IPR024435 Histidyl tRNA synthetase-related domain;IPR036621 Anticodon-binding domain superfamily;IPR041715 Class II Histidinyl-tRNA synthetase (HisRS)-like catalytic core domain
XANPAGTX0501_010496-T1	-3.360677	lichen	MAP kinase-activated protein kinase 2	IPR000253 Forkhead-associated (FHA) domain;IPR000719 Protein kinase domain;IPR008271 Serine/threonine-protein kinase, active site;IPR008984 SMAD/FHA domain superfamily;IPR011009 Protein kinase-like domain superfamily

• All other MAPKs that were found in the genome aren’t DGE

funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>% 
  filter(grepl("IPR017240",InterPro)|grepl("IPR003527",InterPro) | 
          grepl( "IPR008352",InterPro) | grepl( "IPR038783",InterPro)) %>%
  select(TranscriptID,b,change,Product,InterPro) %>%
kable(format = "html", col.names = c("TranscriptID","b","change","product","InterPro")) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

TranscriptID	b	change	product	InterPro
XANPAGTX0501_003276-T1	-0.2487408	low_logFC	mitogen-activated serine/threonine-protein kinase	IPR000719 Protein kinase domain;IPR003527 Mitogen-activated protein (MAP) kinase, conserved site;IPR008271 Serine/threonine-protein kinase, active site;IPR011009 Protein kinase-like domain superfamily;IPR017441 Protein kinase, ATP binding site
XANPAGTX0501_003462-T1	NA	NA	mitogen activated protein kinase	IPR000719 Protein kinase domain;IPR003527 Mitogen-activated protein (MAP) kinase, conserved site;IPR008271 Serine/threonine-protein kinase, active site;IPR011009 Protein kinase-like domain superfamily;IPR017441 Protein kinase, ATP binding site
XANPAGTX0501_009386-T1	NA	NA	Suppressor of Sensor Kinase (SLN1)	IPR000719 Protein kinase domain;IPR008271 Serine/threonine-protein kinase, active site;IPR011009 Protein kinase-like domain superfamily;IPR017240 Mitogen-activated protein (MAP) kinase kinase kinase Ssk2/Ssk22;IPR017441 Protein kinase, ATP binding site
XANPAGTX0501_010261-T1	0.5642185	low_logFC	MAPK protein hog1	IPR000719 Protein kinase domain;IPR003527 Mitogen-activated protein (MAP) kinase, conserved site;IPR008271 Serine/threonine-protein kinase, active site;IPR008352 Mitogen-activated protein (MAP) kinase p38-like;IPR011009 Protein kinase-like domain superfamily;IPR017441 Protein kinase, ATP binding site;IPR038783 Fungal mitogen-activated protein (MAP) kinase Sty1/Hog1
XANPAGTX0501_010261-T2	-0.4922589	low_logFC	MAPK protein hog1, variant 2	IPR000719 Protein kinase domain;IPR003527 Mitogen-activated protein (MAP) kinase, conserved site;IPR008271 Serine/threonine-protein kinase, active site;IPR008352 Mitogen-activated protein (MAP) kinase p38-like;IPR011009 Protein kinase-like domain superfamily;IPR017441 Protein kinase, ATP binding site;IPR038783 Fungal mitogen-activated protein (MAP) kinase Sty1/Hog1

• The remaining kinases in culture are both undefined any further

funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>% 
  filter(grepl("IPR000719",InterPro),change =="culture") %>%
  filter(!grepl("IPR008271",InterPro)) %>% 
  select(TranscriptID,b,change,Product,InterPro) %>%
kable(format = "html", col.names = c("TranscriptID","b","change","product","InterPro")) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

TranscriptID	b	change	product	InterPro
XANPAGTX0501_000132-T1	3.167267	culture	hypothetical protein	IPR000719 Protein kinase domain;IPR011009 Protein kinase-like domain superfamily
XANPAGTX0501_005889-T1	3.211218	culture	hypothetical protein	IPR000719 Protein kinase domain;IPR011009 Protein kinase-like domain superfamily

• In lichens, those are:
  • two of them are not defined further
  • one AGC-kinase, one Tyr kinase
  • one with HeLo domain, one with Ankyrin and TPR repeats, one with von Willebrand factor A-like domain (from blood proteins)

funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>% 
  filter(grepl("IPR000719",InterPro),change =="lichen") %>%
  filter(!grepl("IPR008271",InterPro)) %>% 
  select(TranscriptID,b,change,Product,InterPro) %>%
kable(format = "html", col.names = c("TranscriptID","b","change","product","InterPro")) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

TranscriptID	b	change	product	InterPro
XANPAGTX0501_001006-T1	-3.826268	lichen	hypothetical protein	IPR000719 Protein kinase domain;IPR011009 Protein kinase-like domain superfamily;IPR029498 Prion-inhibition and propagation, HeLo domain;IPR038305 HeLo domain superfamily
XANPAGTX0501_001007-T1	-3.548226	lichen	hypothetical protein	IPR000719 Protein kinase domain;IPR002110 Ankyrin repeat;IPR011009 Protein kinase-like domain superfamily;IPR011990 Tetratricopeptide-like helical domain superfamily;IPR013026 None;IPR019734 Tetratricopeptide repeat;IPR020683 Domain of unknown function DUF3447;IPR036770 Ankyrin repeat-containing domain superfamily
XANPAGTX0501_004853-T1	-1.196511	lichen	hypothetical protein	IPR000719 Protein kinase domain;IPR000961 AGC-kinase, C-terminal;IPR011009 Protein kinase-like domain superfamily
XANPAGTX0501_009558-T1	-1.573738	lichen	hypothetical protein	IPR000719 Protein kinase domain;IPR011009 Protein kinase-like domain superfamily;IPR036465 von Willebrand factor A-like domain superfamily
XANPAGTX0501_010435-T1	-1.088118	lichen	hypothetical protein	IPR000719 Protein kinase domain;IPR011009 Protein kinase-like domain superfamily
XANPAGTX0501_010556-T1	-2.886129	lichen	hypothetical protein	IPR000719 Protein kinase domain;IPR011009 Protein kinase-like domain superfamily
XANPAGTX0501_010558-T1	-3.182102	lichen	hypothetical protein	IPR000719 Protein kinase domain;IPR008266 Tyrosine-protein kinase, active site;IPR011009 Protein kinase-like domain superfamily

4.7. Transporters

Sugar and polyol transporters

• In total, the genome has 38 proteins from the Major facilitator, sugar transporter-like family. This is in line with what Philipp identified in other lecanoromycetes. Of them, 5 are from lichen-enriched orthogroups

funannot2 %>% filter(grepl("IPR005828",InterPro_new)) %>% group_by(lichen_ortho) %>% summarize(n=n())

## # A tibble: 2 × 2
##   lichen_ortho     n
##   <lgl>        <int>
## 1 FALSE           33
## 2 TRUE             5

• List all lichen-specific

funannot2 %>% filter(grepl("IPR005828",InterPro_new),lichen_ortho==T) %>% select(TranscriptID,InterPro_new)

##             TranscriptID
## 1 XANPAGTX0501_001653-T1
## 2 XANPAGTX0501_005571-T1
## 3 XANPAGTX0501_005572-T1
## 4 XANPAGTX0501_008617-T1
## 5 XANPAGTX0501_010000-T1
##                                                                                                                                                                                                                    InterPro_new
## 1 IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily
## 2                                              IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily
## 3                                                                                    IPR005828 Major facilitator, sugar transporter-like, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily
## 4 IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily
## 5                                              IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily

• Six of them upregulated in lichen, 2 in culture

funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>%
  filter(grepl("IPR005828",InterPro_new)) %>% group_by(change) %>% summarize(n=n())

## # A tibble: 4 × 2
##   change        n
##   <chr>     <int>
## 1 culture       2
## 2 lichen        6
## 3 low_logFC    16
## 4 <NA>         14

• Of the 5 lichen-enriched, 3 were upregulated in lichens

funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>%
  filter(grepl("IPR005828",InterPro_new),lichen_ortho==T) %>% group_by(change) %>% summarize(n=n())

## # A tibble: 2 × 2
##   change        n
##   <chr>     <int>
## 1 lichen        3
## 2 low_logFC     2

• Remaining 2 were more present in lichen, but had b-valie between -1 and 0

funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>%
  filter(grepl("IPR005828",InterPro_new),lichen_ortho==T) %>% select(TranscriptID,change,b,qval)

##             TranscriptID    change          b         qval
## 1 XANPAGTX0501_001653-T1    lichen -2.0408199 3.742386e-12
## 2 XANPAGTX0501_005571-T1    lichen -1.9797831 6.700776e-05
## 3 XANPAGTX0501_005572-T1    lichen -1.9025473 1.986579e-05
## 4 XANPAGTX0501_008617-T1 low_logFC -0.5728169 3.266494e-07
## 5 XANPAGTX0501_010000-T1 low_logFC -0.6135197 2.741270e-04

• Identitified putative polyol transporter with blast.
  • Used 4 proteins as queries, following Philipp: “AAX98668.1; from Ambrosiozyma monospora, CAR65543.1, CAG86001.1; from Debaryomyces hansenii, NP_010036.1; from Saccharomyces cerevisiae”, saved as analysis_and_temp_files/08_dge_culture_lichen/blastp_polyol_transporters.txt

sbatch --mem=5G -c 1 --wrap="source package d6092385-3a81-49d9-b044-8ffb85d0c446; blastp -query analysis_and_temp_files/08_dge_culture_lichen/polyol_transporters_genbank.fa -subject ../02_mycobiont_genome/analysis_and_temp_files/06_annotate_lecanoro/GTX0501_pred/annotate_results/Xanthoria_parietina_GTX0501.proteins.fa -outfmt 6 -out analysis_and_temp_files/08_dge_culture_lichen/blastp_polyol_transporters.txt -evalue 1e-100"

• Returned 9 proteins (from 8 genes) with matches with e-value<1e-100

polyol_blast<-read.delim2("../analysis_and_temp_files/08_dge_culture_lichen/blastp_polyol_transporters.txt",header=F)
polyol_blast<-polyol_blast %>% select(V1,V2,V11,V12)
colnames(polyol_blast)<-c("query","subject","e-value","score")
polyol_blast

##         query                subject   e-value score
## 1  AAX98668.1 XANPAGTX0501_010000-T1 1.49e-179   516
## 2  AAX98668.1 XANPAGTX0501_001653-T1 5.32e-176   508
## 3  AAX98668.1 XANPAGTX0501_008617-T1 2.52e-114   350
## 4  CAR65543.1 XANPAGTX0501_005996-T1       0.0   602
## 5  CAR65543.1 XANPAGTX0501_007564-T1 9.63e-178   519
## 6  CAR65543.1 XANPAGTX0501_009339-T1 5.39e-151   449
## 7  CAR65543.1 XANPAGTX0501_009339-T2 2.57e-149   442
## 8  CAR65543.1 XANPAGTX0501_000906-T1 4.21e-145   434
## 9  CAR65543.1 XANPAGTX0501_001701-T1 7.68e-133   402
## 10 CAG86001.1 XANPAGTX0501_005996-T1       0.0   591
## 11 CAG86001.1 XANPAGTX0501_007564-T1 2.80e-178   520
## 12 CAG86001.1 XANPAGTX0501_009339-T1 1.51e-152   453
## 13 CAG86001.1 XANPAGTX0501_009339-T2 2.52e-150   445
## 14 CAG86001.1 XANPAGTX0501_000906-T1 3.81e-146   436
## 15 CAG86001.1 XANPAGTX0501_001701-T1 1.48e-132   401

• Of them 3 were from lichen-enriched orthogroups and 1 was DGE and upregulated in lichen (and also from a lichen-enriched orthogroup)

funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>%
  filter(TranscriptID %in% polyol_blast$subject) %>% select(TranscriptID,change,b,qval,lichen_ortho)

##             TranscriptID    change          b         qval lichen_ortho
## 1 XANPAGTX0501_000906-T1      <NA>         NA           NA        FALSE
## 2 XANPAGTX0501_001653-T1    lichen -2.0408199 3.742386e-12         TRUE
## 3 XANPAGTX0501_001701-T1 low_logFC  0.6237851 2.869476e-06        FALSE
## 4 XANPAGTX0501_005996-T1 low_logFC  0.4003563 2.088997e-06        FALSE
## 5 XANPAGTX0501_007564-T1 low_logFC  0.2966283 4.581743e-02        FALSE
## 6 XANPAGTX0501_008617-T1 low_logFC -0.5728169 3.266494e-07         TRUE
## 7 XANPAGTX0501_009339-T1      <NA>         NA           NA        FALSE
## 8 XANPAGTX0501_009339-T2      <NA>         NA           NA        FALSE
## 9 XANPAGTX0501_010000-T1 low_logFC -0.6135197 2.741270e-04         TRUE

plot_bootstrap(so, 
               target_id = "XANPAGTX0501_001653-T1", 
               units = "est_counts", 
               color_by = "condition")

Ammonium transporters

• In total, the genome has 2 proteins from the Ammonium transporter, neither is from lichen-enriched orthogroups

funannot2 %>% filter(grepl("IPR001905",InterPro_new)) %>% group_by(lichen_ortho) %>% summarize(n=n())

## # A tibble: 1 × 2
##   lichen_ortho     n
##   <lgl>        <int>
## 1 FALSE            2

• One of them is upregulated in lichen

funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>%
  filter(grepl("IPR001905",InterPro_new)) %>% select(TranscriptID,change,b,qval)

##             TranscriptID change         b         qval
## 1 XANPAGTX0501_004972-T1 lichen -2.248389 3.681322e-56
## 2 XANPAGTX0501_009385-T1   <NA>        NA           NA

All transporters

• 41 upregulated in lichen, 12 of them (29%) from lichen-enriched orthogroups

transport_lic<-funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>%
  filter(grepl("transport",InterPro_new),change=="lichen") %>% select(TranscriptID,InterPro_new,lichen_ortho)
transport_lic %>% 
  kable(format = "html", col.names = c("TranscriptID","InterPro_new","lichen_ortho")) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

TranscriptID	InterPro_new	lichen_ortho
XANPAGTX0501_000142-T1	IPR011701 Major facilitator superfamily, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_000342-T1	IPR002293 Amino acid/polyamine transporter I	FALSE
XANPAGTX0501_000342-T2	IPR002293 Amino acid/polyamine transporter I	FALSE
XANPAGTX0501_000684-T1	IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_000704-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_001082-T1	IPR004853 Sugar phosphate transporter domain	FALSE
XANPAGTX0501_001448-T1	IPR011701 Major facilitator superfamily, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_001653-T1	IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_002486-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_003065-T3	IPR005178 Organic solute transporter subunit alpha/Transmembrane protein 184	FALSE
XANPAGTX0501_003337-T2	IPR004738 Phosphate permease, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_004383-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_004428-T1	IPR004695 Transporter protein SLAC1/Mae1/ Ssu1/TehA, IPR030185 Malic acid transport protein, IPR038665 Voltage-dependent anion channel superfamily	FALSE
XANPAGTX0501_004624-T1	IPR004737 Nitrate transporter NarK/NarU-like, IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_004972-T1	IPR001905 Ammonium transporter, IPR018047 Ammonium transporter, conserved site, IPR024041 Ammonium transporter AmtB-like domain, IPR029020 Ammonium/urea transporter	FALSE
XANPAGTX0501_004996-T1	IPR002293 Amino acid/polyamine transporter I	FALSE
XANPAGTX0501_005027-T1	IPR003370 Chromate transporter, IPR014047 Chromate transporter, long chain	FALSE
XANPAGTX0501_005378-T1	IPR002293 Amino acid/polyamine transporter I	FALSE
XANPAGTX0501_005489-T1	IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_005571-T1	IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_005572-T1	IPR005828 Major facilitator, sugar transporter-like, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_005708-T1	IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_006293-T1	IPR001958 Tetracycline resistance protein TetA/multidrug resistance protein MdtG, IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_006324-T1	IPR001204 Phosphate transporter	FALSE
XANPAGTX0501_006367-T1	IPR005829 Sugar transporter, conserved site, IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_006527-T1	IPR000791 Acetate transporter GPR1/FUN34/SatP family	FALSE
XANPAGTX0501_007882-T1	IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_007969-T1	IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_008850-T1	IPR003439 ABC transporter-like, ATP-binding domain, IPR003593 AAA+ ATPase domain, IPR010929 CDR ABC transporter, IPR013525 ABC-2 type transporter, IPR017871 ABC transporter-like, conserved site, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR029481 ABC-transporter, N-terminal domain, IPR034001 ATP-binding cassette transporter, PDR-like subfamily G, domain 1, IPR034003 ATP-binding cassette transporter, PDR-like subfamily G, domain 2	FALSE
XANPAGTX0501_009192-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_009193-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_009202-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_009320-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_009472-T1	IPR005018 DOMON domain, IPR006593 Cytochrome b561/ferric reductase transmembrane, IPR015920 Cellobiose dehydrogenase, cytochrome domain, IPR018825 Domain of unknown function DUF2427, IPR036259 MFS transporter superfamily, IPR038697 None	FALSE
XANPAGTX0501_009914-T1	IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_010175-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_010196-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_010381-T1	IPR002293 Amino acid/polyamine transporter I	FALSE
XANPAGTX0501_010444-T1	IPR001958 Tetracycline resistance protein TetA/multidrug resistance protein MdtG, IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_010683-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_010706-T1	IPR003439 ABC transporter-like, ATP-binding domain, IPR003593 AAA+ ATPase domain, IPR011527 ABC transporter type 1, transmembrane domain, IPR017871 ABC transporter-like, conserved site, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR036640 ABC transporter type 1, transmembrane domain superfamily	FALSE

• 35 upregulated in lichen, 3 of them (8.6%) from lichen-enriched orthogroups

transport_cul<-funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>%
  filter(grepl("transport",InterPro_new),change=="culture") %>% select(TranscriptID,InterPro_new,lichen_ortho)
transport_lic %>% 
  kable(format = "html", col.names = c("TranscriptID","InterPro_new","lichen_ortho")) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

TranscriptID	InterPro_new	lichen_ortho
XANPAGTX0501_000142-T1	IPR011701 Major facilitator superfamily, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_000342-T1	IPR002293 Amino acid/polyamine transporter I	FALSE
XANPAGTX0501_000342-T2	IPR002293 Amino acid/polyamine transporter I	FALSE
XANPAGTX0501_000684-T1	IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_000704-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_001082-T1	IPR004853 Sugar phosphate transporter domain	FALSE
XANPAGTX0501_001448-T1	IPR011701 Major facilitator superfamily, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_001653-T1	IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_002486-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_003065-T3	IPR005178 Organic solute transporter subunit alpha/Transmembrane protein 184	FALSE
XANPAGTX0501_003337-T2	IPR004738 Phosphate permease, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_004383-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_004428-T1	IPR004695 Transporter protein SLAC1/Mae1/ Ssu1/TehA, IPR030185 Malic acid transport protein, IPR038665 Voltage-dependent anion channel superfamily	FALSE
XANPAGTX0501_004624-T1	IPR004737 Nitrate transporter NarK/NarU-like, IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_004972-T1	IPR001905 Ammonium transporter, IPR018047 Ammonium transporter, conserved site, IPR024041 Ammonium transporter AmtB-like domain, IPR029020 Ammonium/urea transporter	FALSE
XANPAGTX0501_004996-T1	IPR002293 Amino acid/polyamine transporter I	FALSE
XANPAGTX0501_005027-T1	IPR003370 Chromate transporter, IPR014047 Chromate transporter, long chain	FALSE
XANPAGTX0501_005378-T1	IPR002293 Amino acid/polyamine transporter I	FALSE
XANPAGTX0501_005489-T1	IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_005571-T1	IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_005572-T1	IPR005828 Major facilitator, sugar transporter-like, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_005708-T1	IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_006293-T1	IPR001958 Tetracycline resistance protein TetA/multidrug resistance protein MdtG, IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_006324-T1	IPR001204 Phosphate transporter	FALSE
XANPAGTX0501_006367-T1	IPR005829 Sugar transporter, conserved site, IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_006527-T1	IPR000791 Acetate transporter GPR1/FUN34/SatP family	FALSE
XANPAGTX0501_007882-T1	IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_007969-T1	IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_008850-T1	IPR003439 ABC transporter-like, ATP-binding domain, IPR003593 AAA+ ATPase domain, IPR010929 CDR ABC transporter, IPR013525 ABC-2 type transporter, IPR017871 ABC transporter-like, conserved site, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR029481 ABC-transporter, N-terminal domain, IPR034001 ATP-binding cassette transporter, PDR-like subfamily G, domain 1, IPR034003 ATP-binding cassette transporter, PDR-like subfamily G, domain 2	FALSE
XANPAGTX0501_009192-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_009193-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_009202-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_009320-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_009472-T1	IPR005018 DOMON domain, IPR006593 Cytochrome b561/ferric reductase transmembrane, IPR015920 Cellobiose dehydrogenase, cytochrome domain, IPR018825 Domain of unknown function DUF2427, IPR036259 MFS transporter superfamily, IPR038697 None	FALSE
XANPAGTX0501_009914-T1	IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_010175-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_010196-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_010381-T1	IPR002293 Amino acid/polyamine transporter I	FALSE
XANPAGTX0501_010444-T1	IPR001958 Tetracycline resistance protein TetA/multidrug resistance protein MdtG, IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	TRUE
XANPAGTX0501_010683-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE
XANPAGTX0501_010706-T1	IPR003439 ABC transporter-like, ATP-binding domain, IPR003593 AAA+ ATPase domain, IPR011527 ABC transporter type 1, transmembrane domain, IPR017871 ABC transporter-like, conserved site, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR036640 ABC transporter type 1, transmembrane domain superfamily	FALSE

4.8. All secreted proteins

• Visualized all 608 putative secreted proteins

secreted<-read.delim2("../../04_secretome/analysis_and_temp_files/01_predicting_effectors/all_secreted_list.txt",header=F)
secreted$TranscriptID<-str_replace(secreted$V1,"FUN","XANPAGTX0501")

png("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_secreted_all.png",res=300,width=2000,height=1500)
plot_transcript_heatmap(so, transcripts=secreted$TranscriptID,
                        cluster_transcripts=T,show_rownames=F,
                        clustering_callback = callback)
dev.off()

## pdf 
##   4

knitr::include_graphics("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_secreted_all.png") 

• Of them, 154 (25.3%) are upregulated in lichen and 40 in culture (6.6%)

secreted_sig<-sig %>% filter(target_id %in% secreted$TranscriptID)
secreted_sig %>% group_by(change) %>% summarise(n=n())

## # A tibble: 3 × 2
##   change        n
##   <chr>     <int>
## 1 culture      40
## 2 lichen      154
## 3 low_logFC   192

• In lichen, secreted proteins make 0.1299578 of upregulated genes
  • compared to 0.0543585 across the whole genome
  • the number for upregulated in culture is 0.070922
• Visualize only DGE secreted proteins

secreted<-read.delim2("../../04_secretome/analysis_and_temp_files/01_predicting_effectors/all_secreted_list.txt",header=F)
secreted$TranscriptID<-str_replace(secreted$V1,"FUN","XANPAGTX0501")

png("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_secreted_dge.png",res=300,width=2000,height=1500)
plot_transcript_heatmap(so, transcripts=secreted_sig$target_id[secreted_sig$change!="low_logFC"],
                        cluster_transcripts=T,show_rownames=F,
                        clustering_callback = callback)
dev.off()

## pdf 
##   4

knitr::include_graphics("../analysis_and_temp_files/08_dge_culture_lichen/heatmap_secreted_dge.png") 

• All secreted proteins upregulated in lichen. There are a bunch of lectins there, GHs and other hydrolases, and a killer toxin
  • Most strongly upregulated are a GH128 (beta-1,3-glucanase / laminarinase), lectins, and a toxin

secreted_table_lichen<-secreted_sig %>% 
  filter(change=="lichen") %>% left_join(funannot2,by = c("target_id"="TranscriptID")) %>% select(target_id,b,Product,CAZyme_new,COG_new,EggNog_new,GO.Terms_new,InterPro_new,PFAM_new,Protease_new,KO,lichen_ortho) %>% 
  arrange(b)
secreted_table_lichen %>%
  kable(format = "html", col.names = colnames(secreted_table_lichen)) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

target_id	b	Product	CAZyme_new	COG_new	EggNog_new	GO.Terms_new	InterPro_new	PFAM_new	Protease_new	KO	lichen_ortho
XANPAGTX0501_001127-T1	-6.214566	hypothetical protein	GH128	NA	NA	NA	IPR008979 Galactose-binding-like domain superfamily, IPR017853 Glycoside hydrolase superfamily, IPR024655 Asl1-like, glycosyl hydrolase catalytic domain	PF11790	NA		FALSE
XANPAGTX0501_000655-T1	-6.186697	hypothetical protein	NA	NA	NA	NA	IPR035992 Ricin B-like lectins	NA	NA		FALSE
XANPAGTX0501_009887-T1	-6.152645	hypothetical protein	NA	NA	ENOG503P63W	NA	NA	NA	NA		FALSE
XANPAGTX0501_007865-T1	-5.732812	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_005533-T1	-5.599048	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_010170-T1	-5.061039	hypothetical protein	NA	NA	NA	NA	IPR000772 Ricin B, lectin domain, IPR035992 Ricin B-like lectins	NA	NA		TRUE
XANPAGTX0501_001063-T1	-4.589396	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_009135-T1	-4.527295	hypothetical protein	NA	NA	NA	GO_component: GO:0005576 - extracellular region [Evidence IEA], GO_process: GO:0009405 - pathogenesis [Evidence IEA]	IPR011329 Killer toxin Kp4/SMK, IPR015131 Killer toxin, Kp4	PF09044	NA		FALSE
XANPAGTX0501_005364-T1	-4.400832	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_000656-T1	-4.357565	hypothetical protein	NA	NA	NA	NA	IPR000772 Ricin B, lectin domain, IPR035992 Ricin B-like lectins	NA	NA		TRUE
XANPAGTX0501_002409-T1	-4.088717	hypothetical protein	NA	NA	NA	GO_component: GO:0009277 - fungal-type cell wall [Evidence IEA], GO_function: GO:0005199 - structural constituent of cell wall [Evidence IEA]	IPR001338 Hydrophobin	NA	NA		TRUE
XANPAGTX0501_009189-T1	-4.014594	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_001935-T1	-3.959675	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_006245-T1	-3.929116	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_005061-T1	-3.850853	hypothetical protein	NA	S:(S) Function unknown	ENOG503NVBA	NA	NA	PF13668	NA		FALSE
XANPAGTX0501_001856-T1	-3.823871	hypothetical protein	NA	NA	ENOG503P50I	NA	IPR037176 Osmotin/thaumatin-like superfamily	NA	NA		TRUE
XANPAGTX0501_006282-T1	-3.776836	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_004309-T1	-3.720276	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_004881-T1	-3.693406	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_001015-T1	-3.506517	hypothetical protein	NA	S:(S) Function unknown	ENOG503P58T, ENOG503P74E, ENOG503P76M	GO_process: GO:0042742 - defense response to bacterium [Evidence IEA], GO_process: GO:0050832 - defense response to fungus [Evidence IEA]	IPR001153 Barwin domain, IPR009009 RlpA-like protein, double-psi beta-barrel domain, IPR036908 RlpA-like domain superfamily	PF00967, PF03330	NA		FALSE
XANPAGTX0501_010044-T1	-3.501860	hypothetical protein	NA	Q:(Q) Secondary metabolites biosynthesis, transport and catabolism	ENOG503NTXA	GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR002937 Amine oxidase, IPR036188 FAD/NAD(P)-binding domain superfamily	PF13450	NA		FALSE
XANPAGTX0501_009317-T1	-3.484947	hypothetical protein	NA	NA	NA	NA	IPR008979 Galactose-binding-like domain superfamily	NA	NA		FALSE
XANPAGTX0501_009340-T1	-3.459083	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_006327-T1	-3.436352	hypothetical protein	NA	NA	NA	NA	IPR018466 Yeast cell wall synthesis Kre9/Knh1-like, N-terminal	PF10342	NA		FALSE
XANPAGTX0501_004930-T1	-3.341143	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_002446-T1	-3.286528	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_003765-T1	-3.256318	hypothetical protein	NA	NA	NA	GO_component: GO:0005618 - cell wall [Evidence IEA], GO_function: GO:0005199 - structural constituent of cell wall [Evidence IEA]	IPR000420 Yeast PIR protein repeat	PF00399	NA		FALSE
XANPAGTX0501_005256-T1	-3.224319	hypothetical protein	AA7	C:(C) Energy production and conversion	ENOG503NV4F	GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_function: GO:0050660 - flavin adenine dinucleotide binding [Evidence IEA], GO_function: GO:0071949 - FAD binding [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR006094 FAD linked oxidase, N-terminal, IPR012951 Berberine/berberine-like, IPR016166 FAD-binding domain, PCMH-type, IPR036318 FAD-binding, type PCMH-like superfamily	PF01565, PF08031	NA		TRUE
XANPAGTX0501_006846-T1	-3.098928	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_010449-T1	-2.870515	hypothetical protein	NA	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503P0GD	GO_function: GO:0004222 - metalloendopeptidase activity [Evidence IEA], GO_function: GO:0008237 - metallopeptidase activity [Evidence IEA], GO_process: GO:0006508 - proteolysis [Evidence IEA]	IPR001384 Peptidase M35, deuterolysin, IPR024079 Metallopeptidase, catalytic domain superfamily, IPR029463 Lysine-specific metallo-endopeptidase	PF02102, PF14521	M35		FALSE
XANPAGTX0501_009688-T1	-2.868656	hypothetical protein	NA	NA	NA	GO_component: GO:0005576 - extracellular region [Evidence IEA], GO_function: GO:0030248 - cellulose binding [Evidence IEA], GO_process: GO:0005975 - carbohydrate metabolic process [Evidence IEA]	IPR000254 Cellulose-binding domain, fungal, IPR035971 Cellulose-binding domain superfamily, IPR036908 RlpA-like domain superfamily	PF00734	NA		FALSE
XANPAGTX0501_003270-T1	-2.857225	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_004956-T1	-2.837976	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_005675-T1	-2.825087	hypothetical protein	NA	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NZAM	GO_function: GO:0008237 - metallopeptidase activity [Evidence IEA]	IPR008754 Peptidase M43, pregnancy-associated plasma-A, IPR024079 Metallopeptidase, catalytic domain superfamily	PF05572, PF13688	M43B		FALSE
XANPAGTX0501_000163-T1	-2.730902	hypothetical protein	NA	S:(S) Function unknown	ENOG503NXZU	NA	IPR009078 Ferritin-like superfamily	PF13668	NA		TRUE
XANPAGTX0501_009886-T1	-2.690801	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_009668-T1	-2.648950	hypothetical protein	NA	NA	ENOG503P6EY	NA	NA	NA	NA		FALSE
XANPAGTX0501_001304-T1	-2.616995	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_006142-T1	-2.552912	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_003572-T1	-2.535693	hypothetical protein	CE16	S:(S) Function unknown	ENOG503P02M	GO_function: GO:0016788 - hydrolase activity, acting on ester bonds [Evidence IEA]	IPR001087 GDSL lipase/esterase, IPR036514 SGNH hydrolase superfamily	PF00657	NA		FALSE
XANPAGTX0501_009606-T1	-2.529422	hypothetical protein	NA	NA	ENOG503PMNB	NA	IPR011024 Gamma-crystallin-like	NA	NA		FALSE
XANPAGTX0501_006291-T1	-2.524612	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_008978-T1	-2.518736	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_005573-T1	-2.506069	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_001458-T1	-2.475919	hypothetical protein	NA	G:(G) Carbohydrate transport and metabolism, O:(O) Posttranslational modification, protein turnover, chaperones, S:(S) Function unknown	ENOG503NVEA, ENOG503P073	NA	IPR002889 Carbohydrate-binding WSC, IPR018535 Domain of unknown function DUF1996	PF01822, PF09362	NA		FALSE
XANPAGTX0501_005361-T1	-2.474153	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_007976-T1	-2.346686	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_009683-T1	-2.345949	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_005733-T1	-2.302949	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_010693-T1	-2.297042	hypothetical protein	AA7	C:(C) Energy production and conversion	ENOG503NVX6	GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_function: GO:0050660 - flavin adenine dinucleotide binding [Evidence IEA], GO_function: GO:0071949 - FAD binding [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR006094 FAD linked oxidase, N-terminal, IPR016166 FAD-binding domain, PCMH-type, IPR016167 FAD-binding, type PCMH, subdomain 1, IPR016169 FAD-binding, type PCMH, subdomain 2, IPR036318 FAD-binding, type PCMH-like superfamily	PF01565	NA		TRUE
XANPAGTX0501_007272-T1	-2.264531	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_002412-T1	-2.245791	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_010247-T1	-2.240976	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_007515-T1	-2.210135	hypothetical protein	NA	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NUDE, ENOG503NV31	GO_function: GO:0004190 - aspartic-type endopeptidase activity [Evidence IEA], GO_process: GO:0006508 - proteolysis [Evidence IEA]	IPR001461 Aspartic peptidase A1 family, IPR001969 Aspartic peptidase, active site, IPR021109 Aspartic peptidase domain superfamily, IPR033121 Peptidase family A1 domain, IPR034163 Aspergillopepsin-like catalytic domain	PF00026	A01A		FALSE
XANPAGTX0501_005771-T1	-2.208725	hypothetical protein	GH5	G:(G) Carbohydrate transport and metabolism	ENOG503NYXZ	GO_function: GO:0004553 - hydrolase activity, hydrolyzing O-glycosyl compounds [Evidence IEA], GO_process: GO:0005975 - carbohydrate metabolic process [Evidence IEA]	IPR001547 Glycoside hydrolase, family 5, IPR017853 Glycoside hydrolase superfamily	PF00150	NA		FALSE
XANPAGTX0501_007362-T1	-2.200339	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_010580-T1	-2.189884	hypothetical protein	NA	G:(G) Carbohydrate transport and metabolism	ENOG501RPBK	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR011048 Cytochrome cd1-nitrite reductase-like, haem d1 domain superfamily, IPR015943 WD40/YVTN repeat-like-containing domain superfamily, IPR019405 Lactonase, 7-bladed beta propeller	PF10282	NA		FALSE
XANPAGTX0501_004978-T1	-2.183515	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_001708-T1	-2.176671	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_009730-T1	-2.155593	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_009615-T1	-2.152340	hypothetical protein	NA	NA	NA	NA	IPR035940 CAP superfamily	NA	NA		FALSE
XANPAGTX0501_003873-T1	-2.109258	hypothetical protein	GH25	G:(G) Carbohydrate transport and metabolism	ENOG503P1T2	GO_function: GO:0003796 - lysozyme activity [Evidence IEA], GO_process: GO:0009253 - peptidoglycan catabolic process [Evidence IEA], GO_process: GO:0016998 - cell wall macromolecule catabolic process [Evidence IEA]	IPR002053 Glycoside hydrolase, family 25, IPR017853 Glycoside hydrolase superfamily, IPR018077 Glycoside hydrolase, family 25 subgroup	PF01183	NA		FALSE
XANPAGTX0501_004880-T1	-2.100330	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_002331-T1	-2.094181	hypothetical protein	GH5	G:(G) Carbohydrate transport and metabolism	ENOG503NY10	GO_function: GO:0004553 - hydrolase activity, hydrolyzing O-glycosyl compounds [Evidence IEA], GO_process: GO:0005975 - carbohydrate metabolic process [Evidence IEA]	IPR001547 Glycoside hydrolase, family 5, IPR017853 Glycoside hydrolase superfamily, IPR018087 Glycoside hydrolase, family 5, conserved site	PF00150	NA		FALSE
XANPAGTX0501_007467-T1	-2.047189	hypothetical protein	CE3	G:(G) Carbohydrate transport and metabolism, S:(S) Function unknown	ENOG503NXZG, ENOG503P4E6	NA	IPR013830 SGNH hydrolase-type esterase domain, IPR036514 SGNH hydrolase superfamily	PF00657, PF13472, PF13517	NA		FALSE
XANPAGTX0501_008041-T1	-2.018648	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_010250-T1	-1.956382	hypothetical protein	NA	NA	ENOG503P3M4	NA	NA	NA	NA		FALSE
XANPAGTX0501_004329-T1	-1.953200	hypothetical protein	NA	NA	NA	NA	IPR020915 Uncharacterised protein family UPF0311	PF11578	NA		TRUE
XANPAGTX0501_008875-T1	-1.934027	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_009699-T1	-1.923092	hypothetical protein	GH16	G:(G) Carbohydrate transport and metabolism, O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NZM7, ENOG503PDKW	GO_function: GO:0004553 - hydrolase activity, hydrolyzing O-glycosyl compounds [Evidence IEA], GO_function: GO:0008061 - chitin binding [Evidence IEA], GO_process: GO:0005975 - carbohydrate metabolic process [Evidence IEA]	IPR000757 Glycoside hydrolase family 16, IPR001002 Chitin-binding, type 1, IPR008264 Beta-glucanase, IPR013320 Concanavalin A-like lectin/glucanase domain superfamily, IPR036861 Endochitinase-like superfamily	PF00722	NA		FALSE
XANPAGTX0501_010470-T1	-1.921148	hypothetical protein	GH24	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503P2E0, ENOG503P2RE	GO_function: GO:0003796 - lysozyme activity [Evidence IEA], GO_process: GO:0009253 - peptidoglycan catabolic process [Evidence IEA], GO_process: GO:0016998 - cell wall macromolecule catabolic process [Evidence IEA], GO_process: GO:0019076 - viral release from host cell [Evidence IEA], GO_process: GO:0019835 - cytolysis [Evidence IEA]	IPR002196 Glycoside hydrolase, family 24, IPR009045 Hedgehog signalling/DD-peptidase zinc-binding domain superfamily, IPR023346 Lysozyme-like domain superfamily, IPR033907 Endolysin/autolysin, IPR034690 Endolysin T4 type	PF00959	NA	K01185	FALSE
XANPAGTX0501_000609-T1	-1.909619	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_006349-T1	-1.876403	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_000051-T1	-1.859342	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_002665-T1	-1.843112	hypothetical protein	NA	NA	NA	GO_function: GO:0008237 - metallopeptidase activity [Evidence IEA]	IPR024079 Metallopeptidase, catalytic domain superfamily	NA	NA		TRUE
XANPAGTX0501_001832-T1	-1.829702	hypothetical protein	GH128	NA	NA	NA	IPR017853 Glycoside hydrolase superfamily, IPR024655 Asl1-like, glycosyl hydrolase catalytic domain	PF11790	NA		TRUE
XANPAGTX0501_004372-T1	-1.826518	hypothetical protein	NA	G:(G) Carbohydrate transport and metabolism, T:(T) Signal transduction mechanisms	ENOG503NV5A, ENOG503P0DZ	NA	IPR002018 Carboxylesterase, type B, IPR019819 Carboxylesterase type B, conserved site, IPR019826 Carboxylesterase type B, active site, IPR029058 Alpha/Beta hydrolase fold	PF00135, PF20434	S09X		FALSE
XANPAGTX0501_010022-T1	-1.809156	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_000923-T1	-1.786540	hypothetical protein	NA	P:(P) Inorganic ion transport and metabolism	ENOG503NV06	GO_function: GO:0003993 - acid phosphatase activity [Evidence IEA], GO_function: GO:0046872 - metal ion binding [Evidence IEA]	IPR008963 Purple acid phosphatase-like, N-terminal, IPR018946 PhoD-like phosphatase, metallophosphatase domain, IPR032093 Phospholipase D, N-terminal, IPR038607 PhoD-like superfamily	PF09423, PF16655	NA	K01113	FALSE
XANPAGTX0501_003361-T1	-1.748190	hypothetical protein	NA	NA	ENOG503P519	NA	NA	NA	NA		FALSE
XANPAGTX0501_009511-T1	-1.745629	hypothetical protein	GH16	G:(G) Carbohydrate transport and metabolism, O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NZM7, ENOG503PDKW	GO_function: GO:0004553 - hydrolase activity, hydrolyzing O-glycosyl compounds [Evidence IEA], GO_function: GO:0008061 - chitin binding [Evidence IEA], GO_process: GO:0005975 - carbohydrate metabolic process [Evidence IEA]	IPR000757 Glycoside hydrolase family 16, IPR001002 Chitin-binding, type 1, IPR008264 Beta-glucanase, IPR013320 Concanavalin A-like lectin/glucanase domain superfamily, IPR036861 Endochitinase-like superfamily	PF00722	NA	K01216	FALSE
XANPAGTX0501_008019-T1	-1.720017	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_002191-T1	-1.708273	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_006967-T1	-1.686952	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_005715-T1	-1.646345	hypothetical protein	AA7	C:(C) Energy production and conversion, O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NXN6, ENOG503P15H	GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_function: GO:0050660 - flavin adenine dinucleotide binding [Evidence IEA], GO_function: GO:0071949 - FAD binding [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR006094 FAD linked oxidase, N-terminal, IPR012951 Berberine/berberine-like, IPR016166 FAD-binding domain, PCMH-type, IPR036318 FAD-binding, type PCMH-like superfamily	PF01565, PF08031	NA		FALSE
XANPAGTX0501_006283-T1	-1.624636	hypothetical protein	NA	NA	NA	NA	IPR000772 Ricin B, lectin domain, IPR035992 Ricin B-like lectins	NA	NA		TRUE
XANPAGTX0501_008270-T1	-1.619871	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_005641-T1	-1.614221	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_010366-T1	-1.609971	hypothetical protein	AA9	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NYCR, ENOG503Q4YD	GO_function: GO:0003676 - nucleic acid binding [Evidence IEA], GO_function: GO:0008061 - chitin binding [Evidence IEA]	IPR001002 Chitin-binding, type 1, IPR005103 Auxiliary Activity family 9, IPR013087 Zinc finger C2H2-type, IPR018371 Chitin-binding, type 1, conserved site, IPR036861 Endochitinase-like superfamily	PF00187, PF03443	NA		FALSE
XANPAGTX0501_000467-T1	-1.600285	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_008622-T1	-1.585245	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_004346-T1	-1.568986	hypothetical protein	NA	S:(S) Function unknown	ENOG503NUT8	NA	IPR027589 Choice-of-anchor B domain	NA	NA		FALSE
XANPAGTX0501_006257-T1	-1.562667	hypothetical protein	NA	G:(G) Carbohydrate transport and metabolism	ENOG503NW21	GO_function: GO:0004553 - hydrolase activity, hydrolyzing O-glycosyl compounds [Evidence IEA], GO_process: GO:0005975 - carbohydrate metabolic process [Evidence IEA]	IPR000490 Glycoside hydrolase family 17, IPR017853 Glycoside hydrolase superfamily	PF00332	NA	K01210	FALSE
XANPAGTX0501_007939-T1	-1.548201	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_010021-T1	-1.539151	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_009026-T1	-1.512207	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_003287-T1	-1.493602	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_002186-T1	-1.483447	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_006194-T1	-1.466337	hypothetical protein	NA	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503P7ES	NA	IPR036908 RlpA-like domain superfamily	NA	NA		TRUE
XANPAGTX0501_004515-T1	-1.449838	hypothetical protein	NA	NA	NA	NA	IPR032710 NTF2-like domain superfamily, IPR037401 SnoaL-like domain	PF13577	NA		FALSE
XANPAGTX0501_010040-T1	-1.448217	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_010027-T1	-1.444367	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_009972-T1	-1.430084	hypothetical protein	NA	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503Q3UA	GO_function: GO:0004252 - serine-type endopeptidase activity [Evidence IEA], GO_function: GO:0008236 - serine-type peptidase activity [Evidence IEA], GO_process: GO:0006508 - proteolysis [Evidence IEA]	IPR000209 Peptidase S8/S53 domain, IPR015366 Peptidase S53, activation domain, IPR030400 Sedolisin domain, IPR036852 Peptidase S8/S53 domain superfamily	PF00082, PF09286	S53		TRUE
XANPAGTX0501_001919-T1	-1.411388	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_000162-T1	-1.389788	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_003766-T1	-1.385254	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_003448-T1	-1.383005	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_009936-T1	-1.379267	hypothetical protein	AA5, CBM32	O:(O) Posttranslational modification, protein turnover, chaperones, S:(S) Function unknown	ENOG502I4WM, ENOG503NY8H	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR000421 Coagulation factor 5/8 C-terminal domain, IPR006652 Kelch repeat type 1, IPR008979 Galactose-binding-like domain superfamily, IPR011043 Galactose oxidase/kelch, beta-propeller, IPR013783 Immunoglobulin-like fold, IPR014756 Immunoglobulin E-set, IPR015202 Galactose oxidase-like, Early set domain, IPR037293 Galactose oxidase, central domain superfamily	PF00754, PF01344, PF09118	NA		FALSE
XANPAGTX0501_008146-T1	-1.360688	hypothetical protein	NA	E:(E) Amino acid transport and metabolism, O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503P41K	GO_function: GO:0004185 - serine-type carboxypeptidase activity [Evidence IEA], GO_process: GO:0006508 - proteolysis [Evidence IEA]	IPR001563 Peptidase S10, serine carboxypeptidase, IPR018202 Serine carboxypeptidase, serine active site, IPR029058 Alpha/Beta hydrolase fold	PF00450	S10	K01288	FALSE
XANPAGTX0501_010026-T1	-1.349396	hypothetical protein	NA	S:(S) Function unknown	ENOG503P0BZ	NA	IPR018392 LysM domain, IPR036779 LysM domain superfamily	PF01476	NA		FALSE
XANPAGTX0501_001455-T1	-1.338580	Sperm-associated antigen 4 protein	GH132	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NUJ1	NA	IPR005556 SUN family	PF03856	NA	K01238	FALSE
XANPAGTX0501_002315-T2	-1.329521	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_009690-T1	-1.325638	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_007280-T1	-1.317948	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_004983-T1	-1.308098	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_005133-T1	-1.291558	hypothetical protein	NA	S:(S) Function unknown	ENOG503NXPR	NA	IPR039535 Arylsulfotransferase-like	PF05935, PF14269	NA		FALSE
XANPAGTX0501_000606-T1	-1.268241	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_007268-T1	-1.263293	hypothetical protein	AA7	C:(C) Energy production and conversion, S:(S) Function unknown	ENOG503NXRX, ENOG503PBAU	GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_function: GO:0050660 - flavin adenine dinucleotide binding [Evidence IEA], GO_function: GO:0071949 - FAD binding [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR006094 FAD linked oxidase, N-terminal, IPR012951 Berberine/berberine-like, IPR016166 FAD-binding domain, PCMH-type, IPR016167 FAD-binding, type PCMH, subdomain 1, IPR016169 FAD-binding, type PCMH, subdomain 2, IPR036318 FAD-binding, type PCMH-like superfamily	PF01565, PF08031	NA		TRUE
XANPAGTX0501_004065-T1	-1.250886	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_006382-T1	-1.241749	hypothetical protein	NA	NA	ENOG503P53I	NA	NA	NA	NA		FALSE
XANPAGTX0501_005717-T1	-1.235652	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_008990-T1	-1.228845	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_009689-T1	-1.216985	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_009731-T1	-1.215351	hypothetical protein	GH71	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NVTC	GO_function: GO:0016787 - hydrolase activity [Evidence IEA]	IPR005197 Glycoside hydrolase family 71	PF03659	NA	K08254	FALSE
XANPAGTX0501_008429-T1	-1.195150	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_001183-T1	-1.191723	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_000737-T1	-1.183761	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_010624-T1	-1.176356	hypothetical protein	NA	J:(J) Translation, ribosomal structure and biogenesis	ENOG503NVR9	NA	IPR023631 Amidase signature domain, IPR036928 Amidase signature (AS) superfamily	NA	NA		FALSE
XANPAGTX0501_003606-T1	-1.168749	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_005629-T1	-1.163876	hypothetical protein	NA	S:(S) Function unknown	ENOG503NY4Y	GO_function: GO:0008081 - phosphoric diester hydrolase activity [Evidence IEA], GO_process: GO:0006629 - lipid metabolic process [Evidence IEA]	IPR017946 PLC-like phosphodiesterase, TIM beta/alpha-barrel domain superfamily, IPR030395 Glycerophosphodiester phosphodiesterase domain	PF03009	NA		FALSE
XANPAGTX0501_002565-T1	-1.159972	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_006751-T1	-1.137824	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_010682-T1	-1.134135	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_000697-T1	-1.131109	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_002041-T1	-1.127546	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_006292-T1	-1.107115	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_010443-T1	-1.107115	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_005317-T1	-1.102348	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_002543-T1	-1.098046	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_006860-T1	-1.097166	hypothetical protein	NA	NA	NA	NA	IPR008979 Galactose-binding-like domain superfamily	NA	NA		FALSE
XANPAGTX0501_007655-T1	-1.094363	hypothetical protein	NA	S:(S) Function unknown	ENOG503NV1P	GO_function: GO:0008081 - phosphoric diester hydrolase activity [Evidence IEA], GO_process: GO:0006629 - lipid metabolic process [Evidence IEA]	IPR017946 PLC-like phosphodiesterase, TIM beta/alpha-barrel domain superfamily	NA	NA		FALSE
XANPAGTX0501_001970-T1	-1.089366	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_009607-T1	-1.069439	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_010370-T1	-1.066233	hypothetical protein	NA	NA	NA	NA	IPR003609 PAN/Apple domain	PF00024	NA		FALSE
XANPAGTX0501_002412-T2	-1.065097	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_003285-T1	-1.064411	hypothetical protein	NA	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503NV2A	GO_function: GO:0008236 - serine-type peptidase activity [Evidence IEA], GO_process: GO:0006508 - proteolysis [Evidence IEA]	IPR008758 Peptidase S28, IPR029058 Alpha/Beta hydrolase fold, IPR042269 Serine carboxypeptidase S28, SKS domain	NA	S28	K09649	FALSE
XANPAGTX0501_000434-T1	-1.045784	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_003186-T1	-1.045733	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_009011-T1	-1.036787	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_002514-T1	-1.030316	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_008683-T1	-1.021294	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_009311-T1	-1.019264	hypothetical protein	NA	NA	NA	NA	IPR008427 Extracellular membrane protein, CFEM domain	PF05730	NA		TRUE
XANPAGTX0501_008027-T1	-1.017996	hypothetical protein	NA	S:(S) Function unknown	ENOG503NZ6V	GO_function: GO:0004601 - peroxidase activity [Evidence IEA]	IPR000028 Chloroperoxidase, IPR036851 Chloroperoxidase-like superfamily	PF01328	NA		FALSE
XANPAGTX0501_003124-T1	-1.008637	hypothetical protein	NA	O:(O) Posttranslational modification, protein turnover, chaperones	ENOG503P2G1	GO_function: GO:0004190 - aspartic-type endopeptidase activity [Evidence IEA], GO_process: GO:0006508 - proteolysis [Evidence IEA]	IPR001461 Aspartic peptidase A1 family, IPR001969 Aspartic peptidase, active site, IPR021109 Aspartic peptidase domain superfamily, IPR033121 Peptidase family A1 domain, IPR034164 Pepsin-like domain	PF00026	A01A		FALSE

• All secreted proteins upregulated in culture, arranged by b value. Mostly enzymes
  • Most strongly upregulated are AA7, AA5, GH128 and galactose-binding enzymes

secreted_table_culture<-secreted_sig %>% 
  filter(change=="culture") %>% left_join(funannot2,by = c("target_id"="TranscriptID")) %>% select(target_id,b,Product,CAZyme_new,COG_new,EggNog_new,GO.Terms_new,InterPro_new,PFAM_new,Protease_new,KO,lichen_ortho) %>%
  arrange(desc(b))
secreted_table_culture %>%
  kable(format = "html", col.names = colnames(secreted_table_culture)) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

target_id	b	Product	CAZyme_new	COG_new	EggNog_new	GO.Terms_new	InterPro_new	PFAM_new	Protease_new	KO	lichen_ortho
XANPAGTX0501_005691-T1	5.859572	hypothetical protein	AA7	C:(C) Energy production and conversion	ENOG503NVX6	GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_function: GO:0050660 - flavin adenine dinucleotide binding [Evidence IEA], GO_function: GO:0071949 - FAD binding [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR006094 FAD linked oxidase, N-terminal, IPR016166 FAD-binding domain, PCMH-type, IPR016167 FAD-binding, type PCMH, subdomain 1, IPR016169 FAD-binding, type PCMH, subdomain 2, IPR036318 FAD-binding, type PCMH-like superfamily	PF01565	NA		TRUE
XANPAGTX0501_005118-T1	5.651733	hypothetical protein	NA	NA	ENOG503PWV2, ENOG503PYSR	NA	NA	NA	NA		TRUE
XANPAGTX0501_006848-T1	3.980717	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_008294-T1	3.732327	hypothetical protein	AA5, CBM32	O:(O) Posttranslational modification, protein turnover, chaperones, S:(S) Function unknown	ENOG502I4WM, ENOG503NY8H	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR000421 Coagulation factor 5/8 C-terminal domain, IPR006652 Kelch repeat type 1, IPR008979 Galactose-binding-like domain superfamily, IPR011043 Galactose oxidase/kelch, beta-propeller, IPR013783 Immunoglobulin-like fold, IPR014756 Immunoglobulin E-set, IPR015202 Galactose oxidase-like, Early set domain, IPR037293 Galactose oxidase, central domain superfamily	PF00754, PF01344, PF09118	NA		FALSE
XANPAGTX0501_010474-T1	3.724444	hypothetical protein	NA	NA	NA	NA	IPR008979 Galactose-binding-like domain superfamily	NA	NA		FALSE
XANPAGTX0501_003863-T2	3.301034	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_000306-T1	3.231592	hypothetical protein	NA	S:(S) Function unknown	ENOG503P21A	NA	IPR021851 Protein of unknown function DUF3455	PF11937	NA		FALSE
XANPAGTX0501_006869-T1	3.075100	hypothetical protein	GH128	NA	NA	NA	IPR008979 Galactose-binding-like domain superfamily, IPR017853 Glycoside hydrolase superfamily, IPR024655 Asl1-like, glycosyl hydrolase catalytic domain	PF11790	NA		FALSE
XANPAGTX0501_005759-T1	2.880832	hypothetical protein	NA	NA	ENOG503P558	NA	NA	NA	NA		FALSE
XANPAGTX0501_009761-T1	2.701300	hypothetical protein	NA	S:(S) Function unknown	ENOG503NZQD	GO_component: GO:0005576 - extracellular region [Evidence IEA]	IPR001283 Cysteine-rich secretory protein-related, IPR014044 CAP domain, IPR018244 Allergen V5/Tpx-1-related, conserved site, IPR034120 None, IPR035940 CAP superfamily	PF00188	NA	K20412	FALSE
XANPAGTX0501_000850-T1	2.534878	hypothetical protein	NA	NA	ENOG503P7C3	NA	NA	NA	NA		FALSE
XANPAGTX0501_006926-T1	2.528494	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		TRUE
XANPAGTX0501_009613-T1	2.515673	hypothetical protein	NA	S:(S) Function unknown	ENOG503NZZ0	NA	IPR000073 Alpha/beta hydrolase fold-1, IPR029058 Alpha/Beta hydrolase fold	PF12697	NA		TRUE
XANPAGTX0501_010126-T2	2.407552	hypothetical protein	NA	NA	NA	GO_function: GO:0008237 - metallopeptidase activity [Evidence IEA]	IPR024079 Metallopeptidase, catalytic domain superfamily	NA	NA		FALSE
XANPAGTX0501_009170-T1	2.253664	hypothetical protein	GH45	G:(G) Carbohydrate transport and metabolism	ENOG503P08U, ENOG503Q3X3	GO_function: GO:0008810 - cellulase activity [Evidence IEA], GO_process: GO:0005975 - carbohydrate metabolic process [Evidence IEA]	IPR000334 Glycoside hydrolase, family 45, IPR036908 RlpA-like domain superfamily	PF02015	NA		FALSE
XANPAGTX0501_001974-T1	2.218747	hypothetical protein	AA7	C:(C) Energy production and conversion	ENOG503NWXH	GO_function: GO:0016491 - oxidoreductase activity [Evidence IEA], GO_function: GO:0050660 - flavin adenine dinucleotide binding [Evidence IEA], GO_function: GO:0071949 - FAD binding [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR006094 FAD linked oxidase, N-terminal, IPR012951 Berberine/berberine-like, IPR016166 FAD-binding domain, PCMH-type, IPR016167 FAD-binding, type PCMH, subdomain 1, IPR016169 FAD-binding, type PCMH, subdomain 2, IPR036318 FAD-binding, type PCMH-like superfamily	PF01565, PF08031	NA		TRUE
XANPAGTX0501_010307-T1	1.956031	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_003850-T1	1.889111	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_009609-T1	1.620965	hypothetical protein	NA	I:(I) Lipid transport and metabolism, S:(S) Function unknown	ENOG503NZ1V	GO_function: GO:0004806 - triglyceride lipase activity [Evidence IEA], GO_process: GO:0016042 - lipid catabolic process [Evidence IEA]	IPR000073 Alpha/beta hydrolase fold-1, IPR005152 Lipase, secreted, IPR022742 Serine aminopeptidase, S33, IPR029058 Alpha/Beta hydrolase fold	PF03583, PF12146, PF12697	NA		TRUE
XANPAGTX0501_010442-T1	1.618450	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_005664-T1	1.551288	hypothetical protein	GH128	NA	NA	NA	IPR008979 Galactose-binding-like domain superfamily, IPR017853 Glycoside hydrolase superfamily, IPR024655 Asl1-like, glycosyl hydrolase catalytic domain	PF11790	NA		FALSE
XANPAGTX0501_007937-T1	1.503271	hypothetical protein	NA	NA	ENOG503NVDR	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR011044 Quinoprotein amine dehydrogenase, beta chain-like, IPR015943 WD40/YVTN repeat-like-containing domain superfamily	NA	NA		FALSE
XANPAGTX0501_000401-T1	1.401801	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_007985-T1	1.397612	hypothetical protein	NA	NA	NA	GO_function: GO:0008237 - metallopeptidase activity [Evidence IEA]	IPR024079 Metallopeptidase, catalytic domain superfamily	NA	NA		FALSE
XANPAGTX0501_006091-T1	1.369228	hypothetical protein	NA	NA	ENOG503P8K1	NA	NA	NA	NA		FALSE
XANPAGTX0501_009962-T1	1.333092	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_007182-T1	1.319524	alpha,alpha-trehalase ath1	NA	G:(G) Carbohydrate transport and metabolism	ENOG503NUMQ	GO_function: GO:0003824 - catalytic activity [Evidence IEA], GO_function: GO:0030246 - carbohydrate binding [Evidence IEA], GO_process: GO:0005975 - carbohydrate metabolic process [Evidence IEA]	IPR005195 Glycoside hydrolase, family 65, central catalytic, IPR005196 Glycoside hydrolase, family 65, N-terminal, IPR008928 Six-hairpin glycosidase superfamily, IPR008979 Galactose-binding-like domain superfamily, IPR011013 Galactose mutarotase-like domain superfamily, IPR012341 Six-hairpin glycosidase-like superfamily, IPR037018 Glycoside hydrolase family 65, N-terminal domain superfamily	PF03633, PF03636	NA		FALSE
XANPAGTX0501_010132-T1	1.308632	hypothetical protein	GH43	G:(G) Carbohydrate transport and metabolism	ENOG503P1F3	GO_function: GO:0004553 - hydrolase activity, hydrolyzing O-glycosyl compounds [Evidence IEA], GO_process: GO:0005975 - carbohydrate metabolic process [Evidence IEA]	IPR006710 Glycoside hydrolase, family 43, IPR023296 Glycosyl hydrolase, five-bladed beta-propellor domain superfamily	PF04616	NA		FALSE
XANPAGTX0501_005244-T1	1.304550	hypothetical protein	AA3	E:(E) Amino acid transport and metabolism	ENOG503NU6B, ENOG503NUFD	GO_function: GO:0016614 - oxidoreductase activity, acting on CH-OH group of donors [Evidence IEA], GO_function: GO:0050660 - flavin adenine dinucleotide binding [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR000172 Glucose-methanol-choline oxidoreductase, N-terminal, IPR007867 Glucose-methanol-choline oxidoreductase, C-terminal, IPR012132 Glucose-methanol-choline oxidoreductase, IPR036188 FAD/NAD(P)-binding domain superfamily	PF00732, PF05199	NA	K00115	FALSE
XANPAGTX0501_007388-T1	1.269375	hypothetical protein	NA	S:(S) Function unknown	ENOG503P3AN	GO_function: GO:0005515 - protein binding [Evidence IEA]	IPR002372 Pyrrolo-quinoline quinone repeat, IPR011047 Quinoprotein alcohol dehydrogenase-like superfamily, IPR015943 WD40/YVTN repeat-like-containing domain superfamily, IPR018391 Pyrrolo-quinoline quinone beta-propeller repeat	NA	NA		FALSE
XANPAGTX0501_006386-T1	1.206100	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE
XANPAGTX0501_002723-T1	1.203666	hypothetical protein	NA	S:(S) Function unknown	ENOG503NXPR	NA	IPR039535 Arylsulfotransferase-like	PF05935, PF14269	NA		FALSE
XANPAGTX0501_006694-T1	1.155895	hypothetical protein	NA	NA	ENOG503P24M	NA	NA	NA	NA		FALSE
XANPAGTX0501_010191-T1	1.151281	hypothetical protein	CE5	G:(G) Carbohydrate transport and metabolism	ENOG503P4Q7	GO_component: GO:0005576 - extracellular region [Evidence IEA], GO_function: GO:0016787 - hydrolase activity [Evidence IEA], GO_function: GO:0050525 - cutinase activity [Evidence IEA]	IPR000675 Cutinase/acetylxylan esterase, IPR011150 Cutinase, monofunctional, IPR029058 Alpha/Beta hydrolase fold	PF01083	NA		FALSE
XANPAGTX0501_001051-T1	1.077085	hypothetical protein	GH17	G:(G) Carbohydrate transport and metabolism	ENOG503NXKT	NA	IPR017853 Glycoside hydrolase superfamily	NA	NA		FALSE
XANPAGTX0501_009124-T1	1.069091	hypothetical protein	NA	S:(S) Function unknown	ENOG503NVXI, ENOG503P4UQ	GO_component: GO:0005618 - cell wall [Evidence IEA], GO_function: GO:0005199 - structural constituent of cell wall [Evidence IEA]	IPR000420 Yeast PIR protein repeat	PF00399	NA		FALSE
XANPAGTX0501_007482-T1	1.051174	hypothetical protein	GH132	S:(S) Function unknown	ENOG503NVKV	NA	IPR005556 SUN family	PF03856	NA		FALSE
XANPAGTX0501_003140-T1	1.035102	hypothetical protein	AA3	E:(E) Amino acid transport and metabolism	ENOG503PBWU	GO_function: GO:0016614 - oxidoreductase activity, acting on CH-OH group of donors [Evidence IEA], GO_function: GO:0050660 - flavin adenine dinucleotide binding [Evidence IEA], GO_process: GO:0055114 - oxidation-reduction process [Evidence IEA]	IPR000172 Glucose-methanol-choline oxidoreductase, N-terminal, IPR007867 Glucose-methanol-choline oxidoreductase, C-terminal, IPR012132 Glucose-methanol-choline oxidoreductase, IPR036188 FAD/NAD(P)-binding domain superfamily	PF00732, PF05199	NA		TRUE
XANPAGTX0501_009902-T1	1.034038	hypothetical protein	NA	P:(P) Inorganic ion transport and metabolism	ENOG503NY8E	NA	IPR001148 Alpha carbonic anhydrase domain, IPR036398 Alpha carbonic anhydrase domain superfamily, IPR041891 Carbonic anhydrase, prokaryotic-like	PF00194	NA	K01672	FALSE
XANPAGTX0501_010393-T1	1.019087	hypothetical protein	NA	NA	NA	NA	NA	NA	NA		FALSE

4.9. Putative NLRs and other self/non-self recognition proteins

Putative NLRs

• Got the list of putative NLRs

nlr_list<-read.delim2("../../02_mycobiont_genome/analysis_and_temp_files/10_nlr/NLRs.txt")

• Four upregulated in lichen, one in cluture

nlr_sig<-sig %>% filter(target_id %in% nlr_list$TranscriptID)
nlr_sig %>% group_by(change) %>% summarise(n=n())

## # A tibble: 3 × 2
##   change        n
##   <chr>     <int>
## 1 culture       1
## 2 lichen        4
## 3 low_logFC     9

• For all lichen-upregulated, we can see they are expressed in culture too

nlr_lichen<-nlr_sig$target_id[nlr_sig$change=="lichen"]
plot_bootstrap(so, 
               target_id = nlr_lichen[1], 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = nlr_lichen[2], 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = nlr_lichen[3], 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = nlr_lichen[4], 
               units = "est_counts", 
               color_by = "condition")

• What kind of NLRs are they?
  • XANPAGTX0501_005494-T1: NACHT + Ankyrin domains
  • XANPAGTX0501_002585-T1: HeLo + NACHT + Ankyrin domains **This is promising: “The HeLo domain of HET-S represents the cell death execution domain in the het-s/het-S system” quote from Daskalov et al. 2012
  • XANPAGTX0501_005102-T1: Nucleoside Phosphotase + NACHT + Ankyrin domains
  • XANPAGTX0501_010687-T1: NACHT + Ankyrin domains
• The one that is culture-upregulated, is inconsistent and is highly-expressed in most lichen samples too

plot_bootstrap(so, 
               target_id = nlr_sig$target_id[nlr_sig$change=="culture"], 
               units = "est_counts", 
               color_by = "condition")

• The protein is NB-ARC + TRP

Broader set of NLR-like proteins

• Got the list of NLR-like proteins, including those without a complete set of domains

nlr_like<-read.delim2("../../02_mycobiont_genome/analysis_and_temp_files/10_nlr/NLR_like.txt")

• 12 upregulated in lichen, 3 in cluture

nlrlike_sig<-sig %>% filter(target_id %in% nlr_like$TranscriptID) %>% arrange(b)
nlrlike_sig %>% group_by(change) %>% summarise(n=n())

## # A tibble: 3 × 2
##   change        n
##   <chr>     <int>
## 1 culture       3
## 2 lichen       12
## 3 low_logFC    14

• Some lichen-upregulated are very strongly upregulated
  • XANPAGTX0501_007753-T1 is not expressed in culture but strongly expressed in nearly all lichen samples. It has one P-loop domain
  • XANPAGTX0501_010570-T1 is not expressed in culture but strongly expressed in nearly all lichen samples. It has P-loop domain + TPR
  • XANPAGTX0501_002436-T1 is expressed in both, but clearly is lichen-upregulated. It has STAND + NACHT domains (STAND function is unknown)

plot_bootstrap(so, 
               target_id = nlrlike_sig$target_id[1], 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = nlrlike_sig$target_id[2], 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = nlrlike_sig$target_id[3], 
               units = "est_counts", 
               color_by = "condition")

Other potential self/non-self recognition proteins

• In total, the genome has 73 proteins with a HET or HaLo domain. Of them, 16 are from lichen-enriched orthogroups

funannot2 %>% filter(grepl("IPR038305",InterPro_new) | 
                       grepl("IPR029498",InterPro_new) | 
                       grepl("IPR010730",InterPro_new)) %>% 
  group_by(lichen_ortho) %>% summarize(n=n())

## # A tibble: 2 × 2
##   lichen_ortho     n
##   <lgl>        <int>
## 1 FALSE           57
## 2 TRUE            16

• Lichen and culture both have some upregulated

het_sig<-funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>%
  filter(grepl("IPR038305",InterPro_new) | 
                       grepl("IPR029498",InterPro_new) | 
                       grepl("IPR010730",InterPro_new)) %>% arrange(b)
het_sig %>% group_by(change) %>% summarize(n=n())

## # A tibble: 4 × 2
##   change        n
##   <chr>     <int>
## 1 culture       6
## 2 lichen       14
## 3 low_logFC    24
## 4 <NA>         29

• Here only showing those proteins not discussed above as NLRs or NLR-like

het_sig2<-het_sig %>% filter(!(TranscriptID %in% nlrlike_sig$target_id),!is.na(b)) 
het_sig2 %>% group_by(change) %>% summarize(n=n())

## # A tibble: 3 × 2
##   change        n
##   <chr>     <int>
## 1 culture       5
## 2 lichen       10
## 3 low_logFC    20

• Visualize most lichen-upregulated
  • Top two have only HET domain
  • The third one has HeLo domains and protein kinase domains

plot_bootstrap(so, 
               target_id = het_sig2$TranscriptID[1], 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = het_sig2$TranscriptID[2], 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = het_sig2$TranscriptID[3], 
               units = "est_counts", 
               color_by = "condition")

* Visualize most culture-upregulated * For first and third, expression in lichens is very non-uniform * Second looks more regular

plot_bootstrap(so, 
               target_id = het_sig2$TranscriptID[nrow(het_sig2)], 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = het_sig2$TranscriptID[nrow(het_sig2)-1], 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = het_sig2$TranscriptID[nrow(het_sig2)-2], 
               units = "est_counts", 
               color_by = "condition")

4.10. Protein ubiquitination

• In addition to already pictured XANPAGTX0501_001643-T1, I wanted to visualize other F-box proteins - primarily to check that they are upregulated among all lichen samples, not just apothecia
  • All seem good, inluding those with the b value most close to the threshold

fbox<-sig2 %>% filter(grepl("F-box",InterPro_new),change!="low_logFC")
plot_bootstrap(so, 
               target_id = fbox$target_id[10], 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = fbox$target_id[9], 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = fbox$target_id[4], 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = fbox$target_id[5], 
               units = "est_counts", 
               color_by = "condition")

poz<-sig2 %>% filter(grepl("BTB/POZ",InterPro_new),change!="low_logFC")
plot_bootstrap(so, 
               target_id = poz$target_id[3], 
               units = "est_counts", 
               color_by = "condition")

4.11. RNAi and RNA binding

• Similarly, wanted to check that they are upregulated among all lichen samples, not just apothecia
  • again, all is good

plot_bootstrap(so, 
               target_id = "XANPAGTX0501_002123-T1", 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = "XANPAGTX0501_003775-T1", 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = "XANPAGTX0501_008184-T1", 
               units = "est_counts", 
               color_by = "condition")

4.12. Apothecia-upregulated transporter

• wanted to check thow looks the profile of the inositol and sugar transporters that is upregulated in apothecia, but not in lichen compared to culture. The stats look legit ( althought the degree of variation for the inositol transporter in the culture is peculiar)

plot_bootstrap(so, 
               target_id = "XANPAGTX0501_001825-T1", 
               units = "est_counts", 
               color_by = "condition")
plot_bootstrap(so, 
               target_id = "XANPAGTX0501_009737-T1", 
               units = "est_counts", 
               color_by = "condition")

4.13. TFs

• Are there any patterns in which TFs are upregulated where? NB: this table have duplicates, i.e. if a protein has two TF domains it’s counted twice
  • “Transcription factor domain, fungi” is a domain that mostly occurs in proteins also classified as C2H2 or Zn2C6

mult_gene_table %>% left_join(sig,by=c("TranscriptID"="target_id")) %>%
  filter(Function=="Transcription factors") %>%
  group_by(change,Description) %>% summarize(n=n()) %>%
  pivot_wider(names_from = change,values_from = n,values_fill=0) %>%
  filter(culture!=0 | lichen!=0)

## `summarise()` has grouped output by 'change'. You can override using the
## `.groups` argument.

## # A tibble: 9 × 5
##   Description                                     culture lichen low_logFC  `NA`
##   <chr>                                             <int>  <int>     <int> <int>
## 1 Basic-leucine zipper domain                           1      0        10     7
## 2 DNA binding HTH domain, Psq-type                      1      0         0     0
## 3 Fungal transcription factor                           3      1         7     9
## 4 Helix-loop-helix DNA-binding domain superfamily       1      0         0     6
## 5 Zinc finger C2H2-type                                 1      9        36    41
## 6 Zinc finger, RING/FYVE/PHD-type                       1      4        41    60
## 7 Zn(2)-C6 fungal-type DNA-binding domain superf…       9      6        37    37
## 8 Homeobox domain                                       0      1         4     0
## 9 Transcription factor domain, fungi                    0      2        21    21

• Look at Zinc finger C2H2-type specifically

funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>% 
  filter(grepl("IPR013087",InterPro),change %in% c("lichen","culture")) %>%
  select(TranscriptID,b,change,Product,InterPro) %>%
kable(format = "html", col.names = c("TranscriptID","b","change","product","InterPro")) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

TranscriptID	b	change	product	InterPro
XANPAGTX0501_000420-T1	-1.619168	lichen	hypothetical protein	IPR013087 Zinc finger C2H2-type
XANPAGTX0501_000984-T1	-3.164451	lichen	hypothetical protein	IPR002151 Kinesin light chain;IPR011990 Tetratricopeptide-like helical domain superfamily;IPR013026 None;IPR013087 Zinc finger C2H2-type;IPR019734 Tetratricopeptide repeat
XANPAGTX0501_001247-T1	-2.397327	lichen	hypothetical protein	IPR013087 Zinc finger C2H2-type;IPR036236 Zinc finger C2H2 superfamily
XANPAGTX0501_001515-T1	-1.263312	lichen	hypothetical protein	IPR013087 Zinc finger C2H2-type
XANPAGTX0501_006931-T1	-1.314529	lichen	hypothetical protein	IPR013087 Zinc finger C2H2-type
XANPAGTX0501_007754-T1	-2.683149	lichen	hypothetical protein	IPR013087 Zinc finger C2H2-type;IPR019447 DNA/RNA-binding protein Kin17, WH-like domain;IPR036236 Zinc finger C2H2 superfamily;IPR038254 DNA/RNA-binding protein KIN17, WH-like domain superfamily

• Which TFs are more common in the genome in general?

t<-mult_gene_table %>% left_join(sig,by=c("TranscriptID"="target_id")) %>%
   filter(Function=="Transcription factors") %>% 
  group_by(change,Description) %>% summarize(n=n()) %>%
  pivot_wider(names_from = change,values_from = n,values_fill=0)

## `summarise()` has grouped output by 'change'. You can override using the
## `.groups` argument.

colnames(t)<-c("Description","culture","lichen","low_logFC","Non")
t %>% mutate(sum=culture+lichen+low_logFC+Non) %>%arrange(desc(sum)) %>%
kable(format = "html", col.names = c("Description","culture","lichen","low_logFC","Non","sum")) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

Description	culture	lichen	low_logFC	Non	sum
Zinc finger, RING/FYVE/PHD-type	1	4	41	60	106
Zn(2)-C6 fungal-type DNA-binding domain superfamily	9	6	37	37	89
Zinc finger C2H2-type	1	9	36	41	87
Transcription factor domain, fungi	0	2	21	21	44
Fungal transcription factor	3	1	7	9	20
Basic-leucine zipper domain	1	0	10	7	18
Fork head domain	0	0	5	4	9
Myb domain	0	0	4	4	8
Helix-loop-helix DNA-binding domain superfamily	1	0	0	6	7
Zinc finger, GATA-type	0	0	3	4	7
Transcription factor CBF/NF-Y/archaeal histone domain	0	0	3	3	6
Homeobox domain	0	1	4	0	5
HTH APSES-type DNA-binding domain superfamily	0	0	2	3	5
Zinc finger, TFIIS-type	0	0	1	4	5
Heat shock factor (HSF)-type, DNA-binding	0	0	1	2	3
Zinc finger, MIZ-type	0	0	1	2	3
Zinc finger, NF-X1-type	0	0	3	0	3
Nuclear transcription factor Y subunit A	0	0	2	0	2
PAS fold	0	0	1	1	2
Transcription Factor IIF, Rap30/Rap74, interaction	0	0	1	1	2
Transcription factor TFIIB	0	0	1	1	2
Transcription factor, MADS-box	0	0	2	0	2
p53-like transcription factor, DNA-binding domain superfamily	0	0	1	1	2
DNA-binding RFX-type winged-helix domain	0	0	0	2	2
Transcription factor IIIC subunit 5, HTH domain	0	0	0	2	2
Transcription factor IIS, N-termina	0	0	0	2	2
DNA binding HTH domain, Psq-type	1	0	0	0	1
CP2 transcription factor	0	0	1	0	1
NDT80 DNA-binding domain superfamily	0	0	1	0	1
SNU66/SART1 family	0	0	1	0	1
TFIIH C1-like domain	0	0	1	0	1
Transcription factor IIIC, 90kDa subunit, N-terminal	0	0	1	0	1
Transcription factor Opi1	0	0	1	0	1
Transcription factor TFIIIB component B, Myb domain	0	0	1	0	1
Transcription factor, NFYB/HAP3, conserved site	0	0	1	0	1
Transcription initiation factor IIA, gamma subunit	0	0	1	0	1
Zinc finger, BED-type	0	0	1	0	1
Zinc finger, C5HC2-type	0	0	1	0	1
Zinc finger, GRF-type	0	0	1	0	1
Apoptosis-antagonizing transcription factor, C-terminal	0	0	0	1	1
CCR4-Not complex component, Not1, C-terminal	0	0	0	1	1
DDT domain	0	0	0	1	1
General transcription factor TFIIH, subunit Tfb6	0	0	0	1	1
TEA/ATTS domain	0	0	0	1	1
Transcription factor IIA, alpha/beta subunit	0	0	0	1	1
Transcription factor Nrm1/Whi5	0	0	0	1	1
Transcription factor Spt20	0	0	0	1	1
Transcription factor Ste12	0	0	0	1	1
Transcription factor TFIID, subunit 8, C-terminal	0	0	0	1	1
Transcription factor TFIIE beta subunit, DNA-binding domain	0	0	0	1	1
Transcription factor TFIIH subunit p52/Tfb2	0	0	0	1	1
Transcription factor TFIIIC, triple barrel domain	0	0	0	1	1
Transcription factor, Skn7-like	0	0	0	1	1

• Look into Zinc finger, RING/FYVE/PHD-type

funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>% 
  filter(grepl("IPR013083",InterPro),change %in% c("lichen","culture")) %>%
  select(TranscriptID,b,change,Product,InterPro) %>%
kable(format = "html", col.names = c("TranscriptID","b","change","product","InterPro")) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

TranscriptID	b	change	product	InterPro
XANPAGTX0501_002947-T1	-1.534891	lichen	hypothetical protein	IPR000330 SNF2, N-terminal;IPR001650 Helicase, C-terminal;IPR001841 Zinc finger, RING-type;IPR013083 Zinc finger, RING/FYVE/PHD-type;IPR014001 Helicase superfamily 1/2, ATP-binding domain;IPR017907 Zinc finger, RING-type, conserved site;IPR018957 Zinc finger, C3HC4 RING-type;IPR027417 P-loop containing nucleoside triphosphate hydrolase;IPR038718 SNF2-like, N-terminal domain superfamily
XANPAGTX0501_005479-T1	2.092073	culture	peroxisome bioproteinsis factor 10	IPR001841 Zinc finger, RING-type;IPR006845 Pex, N-terminal;IPR013083 Zinc finger, RING/FYVE/PHD-type;IPR017907 Zinc finger, RING-type, conserved site
XANPAGTX0501_006448-T1	-1.199765	lichen	hypothetical protein	IPR001841 Zinc finger, RING-type;IPR013083 Zinc finger, RING/FYVE/PHD-type
XANPAGTX0501_009436-T1	-1.317000	lichen	hypothetical protein	IPR000330 SNF2, N-terminal;IPR001650 Helicase, C-terminal;IPR001841 Zinc finger, RING-type;IPR013083 Zinc finger, RING/FYVE/PHD-type;IPR014001 Helicase superfamily 1/2, ATP-binding domain;IPR027417 P-loop containing nucleoside triphosphate hydrolase;IPR038718 SNF2-like, N-terminal domain superfamily

• Look into Zn(2)-C6 fungal-type DNA-binding domain superfamily

funannot2 %>% left_join(sig,by=c("TranscriptID"="target_id")) %>% 
  filter(grepl("IPR036864",InterPro),change %in% c("lichen","culture")) %>%
  select(TranscriptID,b,change,Product,InterPro) %>%
kable(format = "html", col.names = c("TranscriptID","b","change","product","InterPro")) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "600px")

TranscriptID	b	change	product	InterPro
XANPAGTX0501_001980-T1	1.496530	culture	hypothetical protein	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain;IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily
XANPAGTX0501_002161-T1	2.266902	culture	hypothetical protein	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain;IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily
XANPAGTX0501_002427-T1	-1.786972	lichen	hypothetical protein	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain;IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily
XANPAGTX0501_002762-T1	1.105893	culture	DNA-binding transcriptional regulator ume6	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain;IPR021858 Fungal transcription factor;IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily
XANPAGTX0501_004715-T1	-1.034993	lichen	Transcriptional regulator of nonfermentable carbon utilization	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain;IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily
XANPAGTX0501_005120-T1	5.474386	culture	hypothetical protein	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain;IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily
XANPAGTX0501_005608-T1	2.365288	culture	hypothetical protein	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain;IPR021858 Fungal transcription factor;IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily
XANPAGTX0501_009300-T1	1.743077	culture	hypothetical protein	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain;IPR021858 Fungal transcription factor;IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily

5. Preparing visuals

Big heatmap, grouped by function

• Since Complexheatmap didn’t allow me to have multile vertical panels united by one top annotation with single clustering, had to make two heatmapes (one split into panels and one whole) and combine manually in AI
• Draw whole heatmap, which will be used for the top annotation and clustering

#make color mapping consistent between different heatmaps
library(circlize)
library(extrafont)
col_fun <- colorRamp2(seq(0,8,length.out = 100), viridis(100))

filt_mat<-subset(trans_mat, rownames(trans_mat) %in% annotation$TranscriptID)
HM_all = Heatmap(filt_mat, show_row_names = F, show_column_names = T, row_title_rot = 0, col=col_fun,top_annotation = ta,heatmap_legend_param = list(title = "Expression: log(TPM)"))

#get the column order
colord<-column_order(HM_all)

## Warning: The heatmap has not been initialized. You might have different results
## if you repeatedly execute this function, e.g. when row_km/column_km was
## set. It is more suggested to do as `ht = draw(ht); column_order(ht)`.

colord<-colnames(filt_mat)[colord]

draw(HM_all)

pdf(file="../results/big_heatmap_unseparated.pdf",width=6,height=6)
draw(HM_all)
dev.off()

## quartz_off_screen 
##                 2

• Draw two halves of the actual heatmaps

#define function
draw_heatmap_by_group<-function(gene_group,annotation_table = annotation_temp,matrix = trans_mat, order = colord){
  list<-annotation_table$TranscriptID[annotation_table$Function==gene_group]
  filt_mat<-subset(matrix, rownames(matrix) %in% list)
  HM = Heatmap(filt_mat, show_row_names = F, show_column_names = T, row_title = gene_group, row_title_rot = 0, col=col_fun,  show_heatmap_legend = FALSE,
    cluster_columns = FALSE,column_order = order,
       column_names_gp = gpar(fontsize = 6, font="Arial"),
    row_title_gp = gpar(fontsize = 7, font="Arial"))
  return(HM)
}


#make a list of all gene groups in the right order
annotation_temp<-annotation %>% left_join(mult_list %>% select(Function, Function_type) %>% unique()) %>% arrange(Function)
annotation_temp$Function_type<-factor(annotation_temp$Function_type,
  levels=c("Fungal multicellularity", "Expression regulation","Signal transduction"),ordered = T)
annotation_temp<-annotation_temp %>% arrange(Function_type)

#rename some of the functions to make shorter
annotation_temp$Function[annotation_temp$Function=="Acetyl-CoA production and metabolism"]<-"Acetyl-CoA production\nand metabolism"
annotation_temp$Function[annotation_temp$Function=="Cell division, proliferation and growth"]<-"Cell division and growth"
annotation_temp$Function[annotation_temp$Function=="Cell surface and cell wall proteins"]<-"Cell wall proteins"
annotation_temp$Function[annotation_temp$Function=="Cell surface and cell wall proteins"]<-"Cell wall proteins"

#apply to all gene groups
l<-lapply(as.vector(unique(annotation_temp$Function)),draw_heatmap_by_group)

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

#add other gene groups, which aren't in the multicellularity list
#protein kinases
kinase_list<-funannot$TranscriptID[grepl("IPR000719",funannot$InterPro_new) & funannot$TranscriptID %in% sig$target_id[sig$change %in% c("lichen","culture")]]
filt_mat_kinase<-subset(trans_mat, rownames(trans_mat) %in% kinase_list)
HM_kinase = Heatmap(filt_mat_kinase, show_row_names = F, show_column_names = T, row_title = "Protein Kinases", row_title_rot = 0, col=col_fun, show_heatmap_legend = FALSE,
       cluster_columns = FALSE,column_order = colord,
       column_names_gp = gpar(fontsize = 6, font="Arial"),
       row_title_gp = gpar(fontsize = 7, font="Arial"))

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

#NLRs
nlr_list<-nlr_sig$target_id[nlr_sig$change %in% c("lichen","culture")]
filt_mat_nlr<-subset(trans_mat, rownames(trans_mat) %in% nlr_list)
HM_nlr = Heatmap(filt_mat_nlr, show_row_names = F, show_column_names = T, row_title = "Putative NLRs", row_title_rot = 0, col=col_fun, show_heatmap_legend = FALSE,
       cluster_columns = FALSE,column_order = colord,
       column_names_gp = gpar(fontsize = 6, font="Arial"),
       row_title_gp = gpar(fontsize = 7, font="Arial"))

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

#Other het-incopatibility
het_list<-het_sig$TranscriptID[het_sig$change %in% c("lichen","culture") & !(het_sig$TranscriptID %in% nlr_list)]
filt_mat_het<-subset(trans_mat, rownames(trans_mat) %in% het_list)
HM_het = Heatmap(filt_mat_het, show_row_names = F, show_column_names = T, row_title = "Other self/non-self\nrecognition", row_title_rot = 0, col=col_fun, show_heatmap_legend = FALSE,
       cluster_columns = FALSE,column_order = colord,
       column_names_gp = gpar(fontsize = 6, font="Arial"),
       row_title_gp = gpar(fontsize = 7, font="Arial"))

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

#replace 4 panels for signaling pathways with one 
signaling_list<-annotation$TranscriptID[annotation$Function %in% c("G-proteins and GPCR", "MAPK signaling pathway","Oxylipins","Velvet")]
filt_mat_signal<-subset(trans_mat, rownames(trans_mat) %in% signaling_list)
HM_signal = Heatmap(filt_mat_signal, show_row_names = F, show_column_names = T, row_title = "Signal transduction", row_title_rot = 0, col=col_fun, show_heatmap_legend = FALSE,
       cluster_columns = FALSE,column_order = colord,
       column_names_gp = gpar(fontsize = 6, font="Arial"),
       row_title_gp = gpar(fontsize = 7, font="Arial"))

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

#draw
ht_list <- l[[4]] %v% l[[5]] %v% l[[7]] %v% l[[6]] %v% l[[3]] %v% l[[8]] %v% 
  l[[20]] %v% l[[14]] %v% l[[1]] %v% l[[11]] %v% l[[2]] %v% l[[15]] %v% l[[16]] %v% l[[19]]  %v% HM_signal %v% HM_kinase %v% HM_nlr %v% HM_het

#draw in two parts
ht_list1 <- l[[4]] %v% l[[5]] %v% l[[7]] %v% l[[6]] %v% l[[3]] %v% l[[8]] %v% 
  l[[20]] %v% l[[14]] %v% l[[1]] %v% l[[11]] %v% l[[2]] 

ht_list2 <- l[[15]] %v% l[[16]] %v% l[[19]]  %v% HM_signal %v% HM_kinase %v% HM_nlr %v% HM_het

draw(ht_list1)

• Export the heat map

pdf(file="../results/big_heatmap_part1.pdf",width=4.25,height=4.5)
draw(ht_list1, newpage = FALSE)
dev.off()

## quartz_off_screen 
##                 2

pdf(file="../results/big_heatmap_part2.pdf",width=4,height=3.5)
draw(ht_list2)
dev.off()

## quartz_off_screen 
##                 2

• Parietin gene cluster

parietin_list<-c("XANPAGTX0501_008850-T1","XANPAGTX0501_008851-T1","XANPAGTX0501_008852-T1","XANPAGTX0501_008853-T1")

filt_mat_parietin<-subset(trans_mat, rownames(trans_mat) %in% parietin_list)
HM_parietin = Heatmap(filt_mat_parietin, show_row_names = T, show_column_names = T,cluster_rows = FALSE, row_title_rot = 0, col=viridis(100), heatmap_legend_param = list(title = "Expression: log(TPM)"), top_annotation = ta)

pdf(file="../results/parietin_heatmap.pdf",width=10,height=2.5)
draw(HM_parietin)
dev.off()

## quartz_off_screen 
##                 2

HM_parietin

• Make new heat map for all DGE secreted proteins

secreted_list<-secreted_sig$target_id[secreted_sig$change!="low_logFC"]
filt_mat_secreted<-subset(trans_mat, rownames(trans_mat) %in% secreted_list)
HM_secreted = Heatmap(filt_mat_secreted, show_row_names = F, show_column_names = T,cluster_rows = T, row_title_rot = 0, col=viridis(100), heatmap_legend_param = list(title = "Expression: log(TPM)"), top_annotation = ta)

pdf(file="../results/secreted_dge_heatmap.pdf",width=10,height=8)
draw(HM_secreted)
dev.off()

## quartz_off_screen 
##                 2

HM_secreted

• Make box plot for the putative effecotr XANPAGTX0501_009887-T1

plot_bootstrap(so, 
               target_id = "XANPAGTX0501_009887-T1", 
               units = "est_counts", 
               color_by = "condition")

* Make heat map for the same effector

filt_mat_eff<-subset(trans_mat, rownames(trans_mat) =="XANPAGTX0501_009887-T1")
HM_eff = Heatmap(filt_mat_eff, show_row_names = F, show_column_names = T,cluster_rows = T, row_title_rot = 0, col=viridis(100), heatmap_legend_param = list(title = "Expression: log(TPM)"), top_annotation = ta)

pdf(file="../results/XANPAGTX0501_009887-T1_heatmap.pdf",width=10,height=2)
draw(HM_eff)
dev.off()

## quartz_off_screen 
##                 2

HM_eff

• Make heatmap for all core biosynthetic genes (regardless of their DGE status)
  • Added manually DGE status in Ai

antismash_core<-antismash_gene_all %>% filter(Core_gene==T) %>%
  left_join(funannot2,relationship = "many-to-many") %>% 
  left_join(sig, by = c("TranscriptID"="target_id")) 


filt_mat_core<-subset(trans_mat, rownames(trans_mat) %in% antismash_core$TranscriptID)

#define row annotation
##for one protein, XANPAGTX0501_001694-T1, we had two annotations since it is a core gene in two cluster: Xp_GTX0501_2_Cluster_6 and Xp_GTX0501_2_Cluster_7. here I picked Xp_GTX0501_2_Cluster_7, since Xp_GTX0501_2_Cluster_6 had two core genes
ra<-data.frame("TranscriptID"=rownames(filt_mat_core)) %>% left_join(antismash_core) %>%
  filter(TranscriptID!="XANPAGTX0501_001694-T1"|Cluster!="Xp_GTX0501_2_Cluster_6") %>%
  select(Description)
ra_colors = c("fungal-RiPP-like"= brewer.pal(8,"Dark2")[1], "NRP-metallophore"= brewer.pal(8,"Dark2")[4], "NRPS"= brewer.pal(8,"Dark2")[3],
       "NRPS-like"= brewer.pal(8,"Dark2")[5], "NRPS,T1PKS"= brewer.pal(8,"Dark2")[7], "T1PKS"= brewer.pal(8,"Dark2")[6], 
           "T3PKS" = brewer.pal(8,"Dark2")[8], "terpene"= brewer.pal(8,"Dark2")[2])
ra = rowAnnotation(df = ra,col = list(Description = ra_colors))

HM_core = Heatmap(filt_mat_core, show_row_names = F, show_column_names = T,
                  row_title_rot = 0, col=col_fun, show_heatmap_legend = FALSE,
      cluster_columns = FALSE,column_order = colord,
       column_names_gp = gpar(fontsize = 6, font="Arial"),
       row_title_gp = gpar(fontsize = 7, font="Arial"),
      top_annotation = ta,
      right_annotation = ra)

## Warning in validGP(list(...)): NAs introduced by coercion

## Warning in validGP(list(...)): NAs introduced by coercion

pdf(file="../results/all_core_SM_heatmap.pdf",width=8,height=8)
draw(HM_core)
dev.off()

## quartz_off_screen 
##                 2

#get order of the rows in the heatmap and match to b values
rord = row_order(HM_core)

## Warning: The heatmap has not been initialized. You might have different results
## if you repeatedly execute this function, e.g. when row_km/column_km was
## set. It is more suggested to do as `ht = draw(ht); row_order(ht)`.

rord<-rownames(filt_mat_core)[rord]
core_dge<-data.frame("TranscriptID"=rord) %>% left_join(antismash_core) %>%
  filter(TranscriptID!="XANPAGTX0501_001694-T1"|Cluster!="Xp_GTX0501_2_Cluster_6") %>%
  select(TranscriptID,b,Description)
head(core_dge)

##             TranscriptID         b      Description
## 1 XANPAGTX0501_001972-T1  2.363522             NRPS
## 2 XANPAGTX0501_001973-T1  2.358272            T1PKS
## 3 XANPAGTX0501_009715-T1  2.760824 fungal-RiPP-like
## 4 XANPAGTX0501_009716-T1  2.958263 fungal-RiPP-like
## 5 XANPAGTX0501_009866-T1        NA          terpene
## 6 XANPAGTX0501_001064-T1 -1.531609 fungal-RiPP-like

• Make a heat map for putative effectors
  • Include all genes from the ‘cluster of interest’ form the clustering of secretome based on the structures

cl_int<-read.delim2("../../04_secretome/analysis_and_temp_files/05_cluster_structures/clustering_results.txt") %>% filter(ClusterID %in% c("cl04","cl16","cl18","cl19","cl20","cl21","cl22","cl23",
                      "cl24","cl24a","cl37","cl38","cl40","cl41","cl42","cl80",
                      "cl29","cl34"),Gene_Expression!="Non-DGE")
filt_mat_int<-subset(trans_mat, rownames(trans_mat) %in% cl_int$ProteinID)

#define row annotation
ra2<-data.frame("ProteinID"=rownames(filt_mat_int)) %>% left_join(cl_int) %>%
  select(ClusterID)

#define color to match the tree
col_cl<-read.delim2("../../04_secretome/analysis_and_temp_files/05_cluster_structures/cluster_col.txt",sep=",") %>% filter(cluster_id %in% cl_int$ClusterID)
ra2_colors<-as.character(col_cl$color)
names(ra2_colors)<-as.character(col_cl$cluster_id)
ra2 = rowAnnotation(df = ra2,col = list(ClusterID = ra2_colors),show_legend = F)
ta2 = HeatmapAnnotation(df=s2c,col = list(condition = ta_colors),show_legend = F)

HM_int = Heatmap(filt_mat_int, show_row_names = T, show_column_names = T,
                  row_title_rot = 0, col=col_fun, show_heatmap_legend = F,
      cluster_columns = FALSE,column_order = colord,
      top_annotation = ta2,
      right_annotation = ra2,
      column_names_gp = gpar(fontsize = 6),
       row_names_gp = gpar(fontsize = 6))

pdf(file="../results/all_secretome_int_heatmap.pdf",width=4,height=4)
draw(HM_int)
dev.off()

## quartz_off_screen 
##                 2

#get order of rows to match to clusters
rord = row_order(HM_int)

## Warning: The heatmap has not been initialized. You might have different results
## if you repeatedly execute this function, e.g. when row_km/column_km was
## set. It is more suggested to do as `ht = draw(ht); row_order(ht)`.

rord<-rownames(filt_mat_int)[rord]
rord2<-data.frame("ProteinID"=rord) %>% left_join(cl_int)

#get number of DGE per cluster of interest
t<-read.delim2("../../04_secretome/analysis_and_temp_files/05_cluster_structures/clustering_results.txt") %>% filter(ClusterID %in% c("cl04","cl16","cl18","cl19","cl20","cl21","cl22","cl23",
                      "cl24","cl24a","cl37","cl38","cl40","cl41","cl42","cl80",
                      "cl29","cl34")) 

t%>% group_by(ClusterID,Gene_Expression) %>% summarise(n=n()) %>%
  pivot_wider(names_from = Gene_Expression,values_from = n,values_fill=0)

## # A tibble: 18 × 3
## # Groups:   ClusterID [18]
##    ClusterID `Non-DGE` `Upregulated in lichen`
##    <chr>         <int>                   <int>
##  1 cl04              6                       2
##  2 cl16              2                       0
##  3 cl18              2                       4
##  4 cl19              3                       1
##  5 cl20              7                       0
##  6 cl21              4                       1
##  7 cl22              0                       2
##  8 cl23              2                       1
##  9 cl24              5                       4
## 10 cl24a             6                       5
## 11 cl29              3                       1
## 12 cl34              3                       1
## 13 cl37              1                       1
## 14 cl38              3                       1
## 15 cl40              1                       1
## 16 cl41              0                       3
## 17 cl42              0                       1
## 18 cl80              1                       1

Check for chromosomal clusters in DGE

• Prep files for CROC
• Used the reference file produced in ../analysis_and_temp_files/09_dge_architecture/

write.table(geneList5,'../analysis_and_temp_files/08_dge_culture_lichen/lichen_upregulated.txt',col.names = F,row.names = F,quote = F)
write.table(geneList6,'../analysis_and_temp_files/08_dge_culture_lichen/culture_upregulated.txt',col.names = F,row.names = F,quote = F)

• Ran CROC. Used defauls parameters:
  • window_size=30000
  • offset=10000
  • pval=0.05
  • min_genes=3
  • multiple correction=Benjamini & Hochberg ``` cd ~/Documents/software/ git clone https://github.com/emepyc/croc cd croc perl croc.pl –reg ~/Documents/Lichen_project_TSL/03_transcriptomic_analysis/analysis_and_temp_files/08_dge_culture_lichen/lichen_upregulated.txt –ref ~/Documents/Lichen_project_TSL/03_transcriptomic_analysis/analysis_and_temp_files/09_dge_architecture/reference.txt

perl croc.pl –reg ~/Documents/Lichen_project_TSL/03_transcriptomic_analysis/analysis_and_temp_files/08_dge_culture_lichen/culture_upregulated.txt –ref ~/Documents/Lichen_project_TSL/03_transcriptomic_analysis/analysis_and_temp_files/09_dge_architecture/reference.txt

* In lichen-upregulated genes, got 92 clusters. 12 of them have only 3 genes, and 83 <10 genes. Maximum count is 19

```r
croc_l<-read.delim("../analysis_and_temp_files/08_dge_culture_lichen/croc_lichen_upregulated.txt",header=F)
croc_l$cluster<-paste0("cluster",1:nrow(croc_l))
croc_l<-croc_l %>% separate_longer_delim(V9, delim = " ") %>% filter(V9!="") %>% 
  select(-c(V7,V8,V2,V3))
colnames(croc_l)<-c("contig","start","end","pval","TranscriptID","cluster")
croc_l %>% group_by(cluster) %>% summarize(n=n()) %>% arrange(desc(n)) %>% head()

## # A tibble: 6 × 2
##   cluster       n
##   <chr>     <int>
## 1 cluster11    19
## 2 cluster9     17
## 3 cluster52    16
## 4 cluster42    14
## 5 cluster92    14
## 6 cluster34    12

• Merge it with functional annotations and secreted status

croc_l2<-croc_l %>% left_join(funannot2) %>% 
  select(cluster,TranscriptID, InterPro_new,secreted_consensus,antiSMASH) 

## Joining with `by = join_by(TranscriptID)`

croc_l2 %>% 
  kable(format = "html", col.names = colnames(croc_l2)) %>%
  kable_styling() %>%
  kableExtra::scroll_box(width = "100%", height = "300px")

cluster	TranscriptID	InterPro_new	secreted_consensus	antiSMASH
cluster1	XANPAGTX0501_000227-T1	IPR001251 CRAL-TRIO lipid binding domain, IPR011074 CRAL/TRIO, N-terminal domain, IPR036273 CRAL/TRIO, N-terminal domain superfamily, IPR036865 CRAL-TRIO lipid binding domain superfamily	FALSE	NA
cluster1	XANPAGTX0501_000228-T1	IPR008949 Isoprenoid synthase domain superfamily	FALSE	NA
cluster1	XANPAGTX0501_000229-T1	NA	FALSE	NA
cluster1	XANPAGTX0501_000230-T1	IPR000092 Polyprenyl synthetase, IPR008949 Isoprenoid synthase domain superfamily, IPR033749 Polyprenyl synthetase, conserved site	FALSE	NA
cluster2	XANPAGTX0501_000414-T1	NA	FALSE	NA
cluster2	XANPAGTX0501_000413-T1	NA	FALSE	NA
cluster2	XANPAGTX0501_000420-T1	IPR013087 Zinc finger C2H2-type	FALSE	NA
cluster2	XANPAGTX0501_000417-T1	NA	FALSE	NA
cluster3	XANPAGTX0501_000443-T1	IPR001680 WD40 repeat, IPR007111 NACHT nucleoside triphosphatase, IPR007751 Domain of unknown function DUF676, lipase-like, IPR011044 Quinoprotein amine dehydrogenase, beta chain-like, IPR011047 Quinoprotein alcohol dehydrogenase-like superfamily, IPR012908 GPI inositol-deacylase PGAP1-like, IPR015943 WD40/YVTN repeat-like-containing domain superfamily, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR029058 Alpha/Beta hydrolase fold, IPR036322 WD40-repeat-containing domain superfamily	FALSE	NA
cluster3	XANPAGTX0501_000443-T2	IPR001680 WD40 repeat, IPR007111 NACHT nucleoside triphosphatase, IPR007751 Domain of unknown function DUF676, lipase-like, IPR011044 Quinoprotein amine dehydrogenase, beta chain-like, IPR011047 Quinoprotein alcohol dehydrogenase-like superfamily, IPR012908 GPI inositol-deacylase PGAP1-like, IPR015943 WD40/YVTN repeat-like-containing domain superfamily, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR029058 Alpha/Beta hydrolase fold, IPR036322 WD40-repeat-containing domain superfamily	FALSE	NA
cluster3	XANPAGTX0501_000447-T1	NA	FALSE	NA
cluster3	XANPAGTX0501_000448-T1	NA	FALSE	NA
cluster4	XANPAGTX0501_000576-T1	IPR006162 Phosphopantetheine attachment site, IPR013968 Polyketide synthase, ketoreductase domain, IPR020806 Polyketide synthase, phosphopantetheine-binding domain, IPR036291 NAD(P)-binding domain superfamily, IPR036736 ACP-like superfamily	FALSE	NA
cluster4	XANPAGTX0501_000577-T1	IPR011032 GroES-like superfamily, IPR013217 Methyltransferase type 12, IPR013968 Polyketide synthase, ketoreductase domain, IPR020807 Polyketide synthase, dehydratase domain, IPR020843 Polyketide synthase, enoylreductase domain, IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily, IPR036291 NAD(P)-binding domain superfamily, IPR042104 Polyketide synthase, dehydratase domain superfamily	FALSE	NA
cluster4	XANPAGTX0501_000578-T1	IPR001227 Acyl transferase domain superfamily, IPR014030 Beta-ketoacyl synthase, N-terminal, IPR014031 Beta-ketoacyl synthase, C-terminal, IPR014043 Acyl transferase, IPR016035 Acyl transferase/acyl hydrolase/lysophospholipase, IPR016036 Malonyl-CoA ACP transacylase, ACP-binding, IPR016039 Thiolase-like, IPR020801 None, IPR020807 Polyketide synthase, dehydratase domain, IPR020841 Polyketide synthase, beta-ketoacyl synthase domain, IPR032821 Polyketide synthase, C-terminal extension, IPR042104 Polyketide synthase, dehydratase domain superfamily	FALSE	NA
cluster4	XANPAGTX0501_000579-T1	IPR001227 Acyl transferase domain superfamily, IPR014030 Beta-ketoacyl synthase, N-terminal, IPR014031 Beta-ketoacyl synthase, C-terminal, IPR014043 Acyl transferase, IPR016035 Acyl transferase/acyl hydrolase/lysophospholipase, IPR016039 Thiolase-like, IPR018201 Beta-ketoacyl synthase, active site, IPR020801 None, IPR020841 Polyketide synthase, beta-ketoacyl synthase domain, IPR032821 Polyketide synthase, C-terminal extension	FALSE	NA
cluster5	XANPAGTX0501_000601-T1	NA	FALSE	NA
cluster5	XANPAGTX0501_000606-T1	NA	TRUE	NA
cluster5	XANPAGTX0501_000602-T1	NA	FALSE	NA
cluster5	XANPAGTX0501_000610-T1	NA	FALSE	NA
cluster5	XANPAGTX0501_000604-T1	NA	FALSE	NA
cluster5	XANPAGTX0501_000605-T1	NA	FALSE	NA
cluster5	XANPAGTX0501_000609-T1	NA	TRUE	NA
cluster5	XANPAGTX0501_000603-T1	IPR006076 FAD dependent oxidoreductase, IPR036188 FAD/NAD(P)-binding domain superfamily	FALSE	NA
cluster6	XANPAGTX0501_000650-T1	NA	FALSE	NA
cluster6	XANPAGTX0501_000655-T1	IPR035992 Ricin B-like lectins	TRUE	NA
cluster6	XANPAGTX0501_000649-T1	NA	FALSE	NA
cluster6	XANPAGTX0501_000656-T1	IPR000772 Ricin B, lectin domain, IPR035992 Ricin B-like lectins	TRUE	NA
cluster6	XANPAGTX0501_000647-T1	IPR000571 Zinc finger, CCCH-type	FALSE	NA
cluster6	XANPAGTX0501_000648-T1	IPR022099 Domain of unknown function DUF3638, IPR022105 Domain of unknown function DUF3645, IPR027417 P-loop containing nucleoside triphosphate hydrolase	FALSE	NA
cluster6	XANPAGTX0501_000654-T1	IPR004843 Calcineurin-like phosphoesterase domain, ApaH type, IPR029052 Metallo-dependent phosphatase-like	FALSE	NA
cluster7	XANPAGTX0501_000758-T1	IPR000757 Glycoside hydrolase family 16, IPR013320 Concanavalin A-like lectin/glucanase domain superfamily	FALSE	NA
cluster7	XANPAGTX0501_000751-T1	NA	FALSE	NA
cluster7	XANPAGTX0501_000757-T1	IPR001173 Glycosyltransferase 2-like, IPR029044 Nucleotide-diphospho-sugar transferases	FALSE	NA
cluster7	XANPAGTX0501_000755-T1	NA	FALSE	NA
cluster8	XANPAGTX0501_000872-T1	NA	FALSE	NA
cluster8	XANPAGTX0501_000873-T1	IPR002347 Short-chain dehydrogenase/reductase SDR, IPR020904 Short-chain dehydrogenase/reductase, conserved site, IPR036291 NAD(P)-binding domain superfamily	FALSE	NA
cluster8	XANPAGTX0501_000874-T1	IPR001525 C-5 cytosine methyltransferase, IPR018117 DNA methylase, C-5 cytosine-specific, active site, IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily, IPR031303 DNA methylase, C-5 cytosine-specific, conserved site	FALSE	NA
cluster8	XANPAGTX0501_000879-T1	IPR005198 Glycoside hydrolase, family 76, IPR008928 Six-hairpin glycosidase superfamily, IPR014480 Mannan endo-1,6-alpha-mannosidase	FALSE	NA
cluster9	XANPAGTX0501_000922-T1	NA	FALSE	Cluster_2
cluster9	XANPAGTX0501_000911-T1	IPR002110 Ankyrin repeat, IPR020683 Domain of unknown function DUF3447, IPR036770 Ankyrin repeat-containing domain superfamily	FALSE	NA
cluster9	XANPAGTX0501_000916-T1	NA	FALSE	Cluster_2
cluster9	XANPAGTX0501_000914-T1	NA	FALSE	Cluster_2
cluster9	XANPAGTX0501_000888-T1	NA	FALSE	NA
cluster9	XANPAGTX0501_000909-T1	NA	FALSE	NA
cluster9	XANPAGTX0501_000899-T1	NA	FALSE	NA
cluster9	XANPAGTX0501_000891-T1	NA	FALSE	NA
cluster9	XANPAGTX0501_000910-T1	NA	FALSE	NA
cluster9	XANPAGTX0501_000892-T1	NA	FALSE	NA
cluster9	XANPAGTX0501_000894-T1	IPR027417 P-loop containing nucleoside triphosphate hydrolase	FALSE	NA
cluster9	XANPAGTX0501_000917-T1	NA	FALSE	Cluster_2
cluster9	XANPAGTX0501_000915-T1	NA	FALSE	Cluster_2
cluster9	XANPAGTX0501_000897-T1	IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily	FALSE	NA
cluster9	XANPAGTX0501_000923-T1	IPR008963 Purple acid phosphatase-like, N-terminal, IPR018946 PhoD-like phosphatase, metallophosphatase domain, IPR032093 Phospholipase D, N-terminal, IPR038607 PhoD-like superfamily	TRUE	Cluster_2
cluster9	XANPAGTX0501_000908-T1	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR011008 Dimeric alpha-beta barrel, IPR025444 Monooxygenase af470-like, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	FALSE	NA
cluster9	XANPAGTX0501_000913-T1	NA	FALSE	Cluster_2
cluster10	XANPAGTX0501_000949-T1	NA	FALSE	NA
cluster10	XANPAGTX0501_000948-T1	NA	FALSE	NA
cluster10	XANPAGTX0501_000952-T1	NA	FALSE	NA
cluster10	XANPAGTX0501_000951-T1	NA	FALSE	NA
cluster11	XANPAGTX0501_006311-T1	NA	FALSE	Cluster_2
cluster11	XANPAGTX0501_006293-T1	IPR001958 Tetracycline resistance protein TetA/multidrug resistance protein MdtG, IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE	Cluster_1
cluster11	XANPAGTX0501_006324-T1	IPR001204 Phosphate transporter	FALSE	Cluster_2
cluster11	XANPAGTX0501_006295-T1	IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily	FALSE	Cluster_1
cluster11	XANPAGTX0501_006314-T1	IPR001646 Pentapeptide repeat	FALSE	Cluster_2
cluster11	XANPAGTX0501_006301-T1	IPR001585 Transaldolase/Fructose-6-phosphate aldolase, IPR013785 Aldolase-type TIM barrel, IPR018225 Transaldolase, active site	FALSE	Cluster_1
cluster11	XANPAGTX0501_006302-T1	IPR036291 NAD(P)-binding domain superfamily	FALSE	Cluster_1
cluster11	XANPAGTX0501_006298-T1	IPR005123 Oxoglutarate/iron-dependent dioxygenase, IPR026992 Non-haem dioxygenase N-terminal domain, IPR027443 Isopenicillin N synthase-like superfamily	FALSE	Cluster_1
cluster11	XANPAGTX0501_006320-T1	NA	FALSE	Cluster_2
cluster11	XANPAGTX0501_006319-T1	IPR001031 Thioesterase, IPR001227 Acyl transferase domain superfamily, IPR006162 Phosphopantetheine attachment site, IPR009081 Phosphopantetheine binding ACP domain, IPR014030 Beta-ketoacyl synthase, N-terminal, IPR014031 Beta-ketoacyl synthase, C-terminal, IPR014043 Acyl transferase, IPR016035 Acyl transferase/acyl hydrolase/lysophospholipase, IPR016036 Malonyl-CoA ACP transacylase, ACP-binding, IPR016039 Thiolase-like, IPR018201 Beta-ketoacyl synthase, active site, IPR020801 None, IPR020806 Polyketide synthase, phosphopantetheine-binding domain, IPR020807 Polyketide synthase, dehydratase domain, IPR020841 Polyketide synthase, beta-ketoacyl synthase domain, IPR029058 Alpha/Beta hydrolase fold, IPR030918 Polyketide product template domain, IPR032088 Starter unit:ACP transacylase, IPR036736 ACP-like superfamily, IPR042104 Polyketide synthase, dehydratase domain superfamily	FALSE	Cluster_2
cluster11	XANPAGTX0501_006304-T1	NA	FALSE	Cluster_1
cluster11	XANPAGTX0501_006317-T1	IPR036388 Winged helix-like DNA-binding domain superfamily, IPR036390 Winged helix DNA-binding domain superfamily	FALSE	Cluster_2
cluster11	XANPAGTX0501_006318-T1	IPR009799 EthD domain, IPR011008 Dimeric alpha-beta barrel	FALSE	Cluster_2
cluster11	XANPAGTX0501_006303-T1	NA	FALSE	Cluster_1
cluster11	XANPAGTX0501_006294-T1	NA	FALSE	Cluster_1
cluster11	XANPAGTX0501_006308-T1	NA	FALSE	Cluster_1
cluster11	XANPAGTX0501_006296-T1	IPR001173 Glycosyltransferase 2-like, IPR029044 Nucleotide-diphospho-sugar transferases	FALSE	Cluster_1
cluster11	XANPAGTX0501_006291-T1	NA	TRUE	Cluster_1
cluster11	XANPAGTX0501_006292-T1	NA	TRUE	Cluster_1
cluster12	XANPAGTX0501_006907-T1	IPR041622 SMODS and SLOG-associating 2TM effector domain, fungi	FALSE	NA
cluster12	XANPAGTX0501_006918-T1	IPR010255 Haem peroxidase superfamily, IPR017972 Cytochrome P450, conserved site, IPR019791 Haem peroxidase, animal-type, IPR034812 Psi-factor producing oxygenase, N-terminal heme peroxidase domain, IPR036396 Cytochrome P450 superfamily	FALSE	NA
cluster12	XANPAGTX0501_006903-T1	NA	FALSE	NA
cluster12	XANPAGTX0501_006917-T1	IPR018712 Domain of unknown function DUF2235	FALSE	NA
cluster12	XANPAGTX0501_006919-T1	NA	FALSE	NA
cluster12	XANPAGTX0501_006904-T1	NA	FALSE	NA
cluster12	XANPAGTX0501_006910-T1	NA	FALSE	NA
cluster12	XANPAGTX0501_006906-T1	IPR024498 Domain of unknown function DUF2786	FALSE	NA
cluster12	XANPAGTX0501_006909-T1	NA	FALSE	NA
cluster12	XANPAGTX0501_006921-T1	NA	FALSE	NA
cluster12	XANPAGTX0501_006922-T1	IPR004313 Acireductone dioxygenase ARD family, IPR011051 RmlC-like cupin domain superfamily, IPR014710 RmlC-like jelly roll fold, IPR027496 Acireductone dioxygenase, eukaryotes	FALSE	NA
cluster13	XANPAGTX0501_006951-T1	NA	FALSE	NA
cluster13	XANPAGTX0501_006950-T1	NA	FALSE	NA
cluster13	XANPAGTX0501_006945-T1	NA	FALSE	NA
cluster13	XANPAGTX0501_006946-T1	NA	FALSE	NA
cluster13	XANPAGTX0501_006957-T1	NA	FALSE	NA
cluster13	XANPAGTX0501_006953-T1	NA	FALSE	NA
cluster14	XANPAGTX0501_006970-T1	NA	FALSE	NA
cluster14	XANPAGTX0501_006972-T1	NA	FALSE	NA
cluster14	XANPAGTX0501_006967-T1	NA	TRUE	NA
cluster14	XANPAGTX0501_006971-T1	NA	FALSE	NA
cluster14	XANPAGTX0501_006974-T1	NA	FALSE	NA
cluster15	XANPAGTX0501_007248-T1	IPR019313 Mediator complex, subunit Med17	FALSE	NA
cluster15	XANPAGTX0501_007251-T1	IPR007111 NACHT nucleoside triphosphatase, IPR027417 P-loop containing nucleoside triphosphate hydrolase	FALSE	NA
cluster15	XANPAGTX0501_007247-T1	IPR000023 Phosphofructokinase domain, IPR012003 ATP-dependent 6-phosphofructokinase, prokaryotic-type, IPR015912 Phosphofructokinase, conserved site, IPR022953 ATP-dependent 6-phosphofructokinase, IPR035966 Phosphofructokinase superfamily	FALSE	NA
cluster15	XANPAGTX0501_007245-T1	NA	FALSE	NA
cluster15	XANPAGTX0501_007244-T1	NA	FALSE	NA
cluster15	XANPAGTX0501_007246-T1	IPR000023 Phosphofructokinase domain, IPR015912 Phosphofructokinase, conserved site, IPR022953 ATP-dependent 6-phosphofructokinase, IPR035966 Phosphofructokinase superfamily	FALSE	NA
cluster15	XANPAGTX0501_007242-T1	NA	FALSE	NA
cluster15	XANPAGTX0501_007253-T1	NA	FALSE	NA
cluster16	XANPAGTX0501_007271-T1	IPR002347 Short-chain dehydrogenase/reductase SDR, IPR036291 NAD(P)-binding domain superfamily	FALSE	Cluster_1
cluster16	XANPAGTX0501_007267-T1	IPR001077 O-methyltransferase domain, IPR016461 O-methyltransferase COMT-type, IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily, IPR036388 Winged helix-like DNA-binding domain superfamily, IPR036390 Winged helix DNA-binding domain superfamily	FALSE	Cluster_1
cluster16	XANPAGTX0501_007272-T1	NA	TRUE	Cluster_1
cluster16	XANPAGTX0501_007268-T1	IPR006094 FAD linked oxidase, N-terminal, IPR012951 Berberine/berberine-like, IPR016166 FAD-binding domain, PCMH-type, IPR016167 FAD-binding, type PCMH, subdomain 1, IPR016169 FAD-binding, type PCMH, subdomain 2, IPR036318 FAD-binding, type PCMH-like superfamily	TRUE	Cluster_1
cluster17	XANPAGTX0501_007313-T1	NA	FALSE	NA
cluster17	XANPAGTX0501_007308-T1	NA	FALSE	NA
cluster17	XANPAGTX0501_007303-T1	IPR018712 Domain of unknown function DUF2235, IPR029058 Alpha/Beta hydrolase fold, IPR036404 Jacalin-like lectin domain superfamily	FALSE	NA
cluster17	XANPAGTX0501_007310-T1	IPR002151 Kinesin light chain, IPR011990 Tetratricopeptide-like helical domain superfamily, IPR013026 None, IPR013087 Zinc finger C2H2-type, IPR019734 Tetratricopeptide repeat	FALSE	NA
cluster17	XANPAGTX0501_007312-T1	NA	FALSE	NA
cluster17	XANPAGTX0501_007311-T1	IPR002182 NB-ARC, IPR010730 Heterokaryon incompatibility, IPR011990 Tetratricopeptide-like helical domain superfamily, IPR013026 None, IPR019734 Tetratricopeptide repeat, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR031352 NACHT-NTPase and P-loop NTPases, N-terminal domain, IPR041664 Orc1-like, AAA ATPase domain	FALSE	NA
cluster17	XANPAGTX0501_007309-T1	IPR040976 Fungal-type protein kinase	FALSE	NA
cluster18	XANPAGTX0501_007344-T1	NA	FALSE	Cluster_2
cluster18	XANPAGTX0501_007361-T1	NA	FALSE	Cluster_2
cluster18	XANPAGTX0501_007362-T1	NA	TRUE	Cluster_2
cluster18	XANPAGTX0501_007353-T1	NA	FALSE	Cluster_2
cluster18	XANPAGTX0501_007349-T1	NA	FALSE	Cluster_2
cluster18	XANPAGTX0501_007351-T1	IPR000873 AMP-dependent synthetase/ligase domain, IPR001242 Condensation domain, IPR009081 Phosphopantetheine binding ACP domain, IPR020845 AMP-binding, conserved site, IPR023213 Chloramphenicol acetyltransferase-like domain superfamily, IPR025110 AMP-binding enzyme, C-terminal domain, IPR036736 ACP-like superfamily, IPR042099 ANL, N-terminal domain	FALSE	Cluster_2
cluster18	XANPAGTX0501_007352-T1	IPR000873 AMP-dependent synthetase/ligase domain, IPR001242 Condensation domain, IPR009081 Phosphopantetheine binding ACP domain, IPR020845 AMP-binding, conserved site, IPR023213 Chloramphenicol acetyltransferase-like domain superfamily, IPR025110 AMP-binding enzyme, C-terminal domain, IPR036736 ACP-like superfamily, IPR042099 ANL, N-terminal domain	FALSE	Cluster_2
cluster18	XANPAGTX0501_007350-T1	IPR020845 AMP-binding, conserved site, IPR042099 ANL, N-terminal domain	FALSE	Cluster_2
cluster18	XANPAGTX0501_007343-T1	NA	FALSE	Cluster_2
cluster19	XANPAGTX0501_007397-T1	NA	FALSE	Cluster_3
cluster19	XANPAGTX0501_007403-T1	NA	FALSE	NA
cluster19	XANPAGTX0501_007404-T1	IPR001002 Chitin-binding, type 1, IPR001223 Glycoside hydrolase family 18, catalytic domain, IPR011583 Chitinase II, IPR017853 Glycoside hydrolase superfamily, IPR036861 Endochitinase-like superfamily	FALSE	NA
cluster19	XANPAGTX0501_007405-T1	IPR001002 Chitin-binding, type 1, IPR002509 NodB homology domain, IPR011330 Glycoside hydrolase/deacetylase, beta/alpha-barrel, IPR017853 Glycoside hydrolase superfamily, IPR018371 Chitin-binding, type 1, conserved site, IPR029070 Chitinase insertion domain superfamily, IPR036852 Peptidase S8/S53 domain superfamily, IPR036861 Endochitinase-like superfamily	FALSE	NA
cluster20	XANPAGTX0501_007872-T1	NA	FALSE	Cluster_1
cluster20	XANPAGTX0501_007870-T1	NA	FALSE	Cluster_1
cluster20	XANPAGTX0501_007865-T1	NA	TRUE	NA
cluster20	XANPAGTX0501_007863-T1	NA	FALSE	NA
cluster20	XANPAGTX0501_007866-T1	NA	FALSE	NA
cluster20	XANPAGTX0501_007862-T1	NA	FALSE	NA
cluster20	XANPAGTX0501_007864-T1	NA	FALSE	NA
cluster20	XANPAGTX0501_007873-T1	NA	FALSE	Cluster_1
cluster20	XANPAGTX0501_007869-T1	IPR000210 BTB/POZ domain, IPR011333 SKP1/BTB/POZ domain superfamily	FALSE	Cluster_1
cluster21	XANPAGTX0501_007923-T1	IPR000608 Ubiquitin-conjugating enzyme E2, IPR016135 Ubiquitin-conjugating enzyme/RWD-like	FALSE	NA
cluster21	XANPAGTX0501_007933-T1	NA	FALSE	NA
cluster21	XANPAGTX0501_007932-T1	NA	FALSE	NA
cluster21	XANPAGTX0501_007929-T1	NA	FALSE	NA
cluster21	XANPAGTX0501_007931-T1	NA	FALSE	NA
cluster21	XANPAGTX0501_007934-T1	NA	FALSE	NA
cluster21	XANPAGTX0501_007930-T1	NA	FALSE	NA
cluster21	XANPAGTX0501_007939-T1	NA	TRUE	NA
cluster22	XANPAGTX0501_007969-T1	IPR003663 Sugar/inositol transporter, IPR005828 Major facilitator, sugar transporter-like, IPR005829 Sugar transporter, conserved site, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE	NA
cluster22	XANPAGTX0501_007973-T1	NA	FALSE	NA
cluster22	XANPAGTX0501_007970-T1	IPR001077 O-methyltransferase domain, IPR016461 O-methyltransferase COMT-type, IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily, IPR036388 Winged helix-like DNA-binding domain superfamily, IPR036390 Winged helix DNA-binding domain superfamily	FALSE	NA
cluster22	XANPAGTX0501_007972-T1	NA	FALSE	NA
cluster22	XANPAGTX0501_007971-T1	NA	FALSE	NA
cluster22	XANPAGTX0501_007976-T1	NA	TRUE	NA
cluster23	XANPAGTX0501_008007-T1	NA	FALSE	NA
cluster23	XANPAGTX0501_008008-T1	NA	FALSE	NA
cluster23	XANPAGTX0501_008009-T1	NA	FALSE	NA
cluster24	XANPAGTX0501_008019-T1	NA	TRUE	NA
cluster24	XANPAGTX0501_008029-T1	NA	FALSE	NA
cluster24	XANPAGTX0501_008031-T1	NA	FALSE	NA
cluster24	XANPAGTX0501_008032-T1	NA	FALSE	NA
cluster24	XANPAGTX0501_008024-T2	IPR007192 Cdc23, IPR011990 Tetratricopeptide-like helical domain superfamily, IPR013026 None, IPR019734 Tetratricopeptide repeat	FALSE	NA
cluster24	XANPAGTX0501_008030-T1	IPR001128 Cytochrome P450, IPR002401 Cytochrome P450, E-class, group I, IPR017972 Cytochrome P450, conserved site, IPR036396 Cytochrome P450 superfamily	FALSE	NA
cluster24	XANPAGTX0501_008041-T1	NA	TRUE	NA
cluster24	XANPAGTX0501_008027-T1	IPR000028 Chloroperoxidase, IPR036851 Chloroperoxidase-like superfamily	TRUE	NA
cluster24	XANPAGTX0501_008018-T1	NA	FALSE	NA
cluster24	XANPAGTX0501_008028-T1	NA	FALSE	NA
cluster25	XANPAGTX0501_008272-T1	IPR000873 AMP-dependent synthetase/ligase domain, IPR006162 Phosphopantetheine attachment site, IPR009081 Phosphopantetheine binding ACP domain, IPR013120 Fatty acyl-coenzyme A reductase, NAD-binding domain, IPR020845 AMP-binding, conserved site, IPR036291 NAD(P)-binding domain superfamily, IPR036736 ACP-like superfamily, IPR042099 ANL, N-terminal domain	FALSE	Cluster_1
cluster25	XANPAGTX0501_008267-T1	IPR024079 Metallopeptidase, catalytic domain superfamily	FALSE	Cluster_1
cluster25	XANPAGTX0501_008268-T1	NA	FALSE	Cluster_1
cluster25	XANPAGTX0501_008274-T1	NA	FALSE	Cluster_1
cluster25	XANPAGTX0501_008270-T1	NA	TRUE	Cluster_1
cluster25	XANPAGTX0501_008273-T1	IPR000873 AMP-dependent synthetase/ligase domain, IPR006162 Phosphopantetheine attachment site, IPR009081 Phosphopantetheine binding ACP domain, IPR013120 Fatty acyl-coenzyme A reductase, NAD-binding domain, IPR020845 AMP-binding, conserved site, IPR036291 NAD(P)-binding domain superfamily, IPR036736 ACP-like superfamily, IPR042099 ANL, N-terminal domain	FALSE	Cluster_1
cluster26	XANPAGTX0501_008284-T1	IPR029044 Nucleotide-diphospho-sugar transferases	FALSE	Cluster_1
cluster26	XANPAGTX0501_008288-T1	NA	FALSE	NA
cluster26	XANPAGTX0501_008289-T1	NA	FALSE	NA
cluster26	XANPAGTX0501_008291-T1	NA	FALSE	NA
cluster27	XANPAGTX0501_008409-T1	IPR001680 WD40 repeat, IPR011659 WD40-like beta propeller, IPR011990 Tetratricopeptide-like helical domain superfamily, IPR013026 None, IPR015943 WD40/YVTN repeat-like-containing domain superfamily, IPR017986 None, IPR019734 Tetratricopeptide repeat, IPR019775 WD40 repeat, conserved site, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR036322 WD40-repeat-containing domain superfamily	FALSE	NA
cluster27	XANPAGTX0501_008413-T1	NA	FALSE	NA
cluster27	XANPAGTX0501_008414-T1	NA	FALSE	NA
cluster27	XANPAGTX0501_008417-T1	IPR002347 Short-chain dehydrogenase/reductase SDR, IPR020904 Short-chain dehydrogenase/reductase, conserved site, IPR036291 NAD(P)-binding domain superfamily	FALSE	NA
cluster27	XANPAGTX0501_008418-T1	IPR023213 Chloramphenicol acetyltransferase-like domain superfamily	FALSE	NA
cluster28	XANPAGTX0501_008435-T1	IPR000073 Alpha/beta hydrolase fold-1, IPR013595 Peptidase S33 tripeptidyl aminopeptidase-like, C-terminal, IPR029058 Alpha/Beta hydrolase fold	FALSE	NA
cluster28	XANPAGTX0501_008438-T1	NA	FALSE	NA
cluster28	XANPAGTX0501_008437-T1	IPR042099 ANL, N-terminal domain	FALSE	NA
cluster28	XANPAGTX0501_008439-T1	IPR003819 TauD/TfdA-like domain, IPR042098 Taurine dioxygenase TauD-like superfamily	FALSE	NA
cluster28	XANPAGTX0501_008436-T1	NA	FALSE	NA
cluster29	XANPAGTX0501_008541-T1	NA	FALSE	NA
cluster29	XANPAGTX0501_008525-T1	NA	FALSE	NA
cluster29	XANPAGTX0501_008533-T1	NA	FALSE	NA
cluster29	XANPAGTX0501_008529-T1	NA	FALSE	NA
cluster29	XANPAGTX0501_008534-T1	NA	FALSE	NA
cluster30	XANPAGTX0501_008676-T1	NA	FALSE	NA
cluster30	XANPAGTX0501_008677-T1	IPR027417 P-loop containing nucleoside triphosphate hydrolase	FALSE	NA
cluster30	XANPAGTX0501_008683-T1	NA	TRUE	NA
cluster31	XANPAGTX0501_008863-T1	NA	FALSE	Cluster_1
cluster31	XANPAGTX0501_008852-T1	IPR001227 Acyl transferase domain superfamily, IPR009081 Phosphopantetheine binding ACP domain, IPR014030 Beta-ketoacyl synthase, N-terminal, IPR014031 Beta-ketoacyl synthase, C-terminal, IPR014043 Acyl transferase, IPR016035 Acyl transferase/acyl hydrolase/lysophospholipase, IPR016036 Malonyl-CoA ACP transacylase, ACP-binding, IPR016039 Thiolase-like, IPR020801 None, IPR020806 Polyketide synthase, phosphopantetheine-binding domain, IPR020841 Polyketide synthase, beta-ketoacyl synthase domain, IPR030918 Polyketide product template domain, IPR032088 Starter unit:ACP transacylase, IPR032821 Polyketide synthase, C-terminal extension, IPR036736 ACP-like superfamily, IPR042104 Polyketide synthase, dehydratase domain superfamily	FALSE	Cluster_1
cluster31	XANPAGTX0501_008851-T1	IPR001279 Metallo-beta-lactamase, IPR036866 Ribonuclease Z/Hydroxyacylglutathione hydrolase-like	FALSE	Cluster_1
cluster31	XANPAGTX0501_008856-T1	IPR001810 F-box domain, IPR032675 Leucine-rich repeat domain superfamily	FALSE	Cluster_1
cluster31	XANPAGTX0501_008850-T1	IPR003439 ABC transporter-like, ATP-binding domain, IPR003593 AAA+ ATPase domain, IPR010929 CDR ABC transporter, IPR013525 ABC-2 type transporter, IPR017871 ABC transporter-like, conserved site, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR029481 ABC-transporter, N-terminal domain, IPR034001 ATP-binding cassette transporter, PDR-like subfamily G, domain 1, IPR034003 ATP-binding cassette transporter, PDR-like subfamily G, domain 2	FALSE	Cluster_1
cluster31	XANPAGTX0501_008853-T1	IPR009799 EthD domain, IPR011008 Dimeric alpha-beta barrel	FALSE	Cluster_1
cluster31	XANPAGTX0501_008855-T1	IPR000210 BTB/POZ domain, IPR011333 SKP1/BTB/POZ domain superfamily	FALSE	Cluster_1
cluster32	XANPAGTX0501_008875-T1	NA	TRUE	NA
cluster32	XANPAGTX0501_008876-T1	NA	FALSE	NA
cluster32	XANPAGTX0501_008877-T1	NA	FALSE	NA
cluster33	XANPAGTX0501_009046-T1	NA	FALSE	NA
cluster33	XANPAGTX0501_009041-T1	IPR002347 Short-chain dehydrogenase/reductase SDR, IPR036291 NAD(P)-binding domain superfamily	FALSE	NA
cluster33	XANPAGTX0501_009040-T1	NA	FALSE	NA
cluster33	XANPAGTX0501_009055-T1	IPR010730 Heterokaryon incompatibility	FALSE	NA
cluster33	XANPAGTX0501_009052-T1	NA	FALSE	NA
cluster33	XANPAGTX0501_009054-T1	NA	FALSE	NA
cluster33	XANPAGTX0501_009050-T1	NA	FALSE	NA
cluster34	XANPAGTX0501_009194-T1	IPR001077 O-methyltransferase domain, IPR016461 O-methyltransferase COMT-type, IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily, IPR036388 Winged helix-like DNA-binding domain superfamily, IPR036390 Winged helix DNA-binding domain superfamily	FALSE	NA
cluster34	XANPAGTX0501_009204-T1	IPR001077 O-methyltransferase domain, IPR016461 O-methyltransferase COMT-type, IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily, IPR036388 Winged helix-like DNA-binding domain superfamily, IPR036390 Winged helix DNA-binding domain superfamily	FALSE	NA
cluster34	XANPAGTX0501_009201-T1	NA	FALSE	NA
cluster34	XANPAGTX0501_009192-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE	NA
cluster34	XANPAGTX0501_009196-T1	NA	FALSE	NA
cluster34	XANPAGTX0501_009202-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE	NA
cluster34	XANPAGTX0501_009199-T1	NA	FALSE	NA
cluster34	XANPAGTX0501_009189-T1	NA	TRUE	NA
cluster34	XANPAGTX0501_009193-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE	NA
cluster34	XANPAGTX0501_009203-T1	IPR001077 O-methyltransferase domain, IPR016461 O-methyltransferase COMT-type, IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily, IPR036388 Winged helix-like DNA-binding domain superfamily, IPR036390 Winged helix DNA-binding domain superfamily	FALSE	NA
cluster34	XANPAGTX0501_009205-T1	NA	FALSE	NA
cluster34	XANPAGTX0501_009195-T1	NA	FALSE	NA
cluster35	XANPAGTX0501_000971-T1	IPR011009 Protein kinase-like domain superfamily	FALSE	NA
cluster35	XANPAGTX0501_000972-T1	NA	FALSE	NA
cluster35	XANPAGTX0501_000974-T1	IPR000573 Aconitase A/isopropylmalate dehydratase small subunit, swivel domain, IPR001030 Aconitase/3-isopropylmalate dehydratase large subunit, alpha/beta/alpha domain, IPR004418 Homoaconitase, mitochondrial, IPR015928 Aconitase/3-isopropylmalate dehydratase, swivel, IPR015931 Aconitase/3-isopropylmalate dehydratase large subunit, alpha/beta/alpha, subdomain 1/3, IPR018136 Aconitase family, 4Fe-4S cluster binding site, IPR036008 Aconitase, iron-sulfur domain, IPR039386 Homoaconitase, swivel domain	FALSE	NA
cluster35	XANPAGTX0501_000978-T1	NA	FALSE	NA
cluster35	XANPAGTX0501_000973-T1	IPR000192 Aminotransferase class V domain, IPR015421 Pyridoxal phosphate-dependent transferase, major domain, IPR015422 Pyridoxal phosphate-dependent transferase, small domain, IPR015424 Pyridoxal phosphate-dependent transferase, IPR022278 Phosphoserine aminotransferase	FALSE	NA
cluster36	XANPAGTX0501_001015-T1	IPR001153 Barwin domain, IPR009009 RlpA-like protein, double-psi beta-barrel domain, IPR036908 RlpA-like domain superfamily	TRUE	NA
cluster36	XANPAGTX0501_001008-T1	NA	FALSE	NA
cluster36	XANPAGTX0501_001017-T1	IPR007111 NACHT nucleoside triphosphatase, IPR024983 CHAT domain, IPR027417 P-loop containing nucleoside triphosphate hydrolase	FALSE	NA
cluster36	XANPAGTX0501_001010-T1	NA	FALSE	NA
cluster36	XANPAGTX0501_001014-T1	NA	FALSE	NA
cluster37	XANPAGTX0501_001063-T1	NA	TRUE	Cluster_1
cluster37	XANPAGTX0501_001064-T1	IPR021765 Mycotoxin biosynthesis protein UstYa-like	FALSE	Cluster_1
cluster37	XANPAGTX0501_001062-T1	NA	FALSE	Cluster_1
cluster37	XANPAGTX0501_001061-T1	IPR002328 Alcohol dehydrogenase, zinc-type, conserved site, IPR011032 GroES-like superfamily, IPR013149 Alcohol dehydrogenase-like, C-terminal, IPR013154 Alcohol dehydrogenase-like, N-terminal, IPR020843 Polyketide synthase, enoylreductase domain, IPR036291 NAD(P)-binding domain superfamily	FALSE	Cluster_1
cluster38	XANPAGTX0501_001178-T1	NA	FALSE	NA
cluster38	XANPAGTX0501_001183-T1	NA	TRUE	NA
cluster38	XANPAGTX0501_001184-T1	NA	FALSE	NA
cluster38	XANPAGTX0501_001185-T1	NA	FALSE	NA
cluster39	XANPAGTX0501_001458-T1	IPR002889 Carbohydrate-binding WSC, IPR018535 Domain of unknown function DUF1996	TRUE	NA
cluster39	XANPAGTX0501_001455-T1	IPR005556 SUN family	TRUE	NA
cluster39	XANPAGTX0501_001453-T1	IPR010255 Haem peroxidase superfamily, IPR019791 Haem peroxidase, animal-type, IPR034812 Psi-factor producing oxygenase, N-terminal heme peroxidase domain, IPR036396 Cytochrome P450 superfamily, IPR037120 Haem peroxidase domain superfamily, animal type	FALSE	NA
cluster39	XANPAGTX0501_001462-T1	IPR008775 Phytanoyl-CoA dioxygenase-like	FALSE	NA
cluster39	XANPAGTX0501_001452-T1	IPR018712 Domain of unknown function DUF2235	FALSE	NA
cluster39	XANPAGTX0501_001451-T1	NA	FALSE	NA
cluster39	XANPAGTX0501_001465-T1	NA	FALSE	NA
cluster39	XANPAGTX0501_001448-T1	IPR011701 Major facilitator superfamily, IPR036259 MFS transporter superfamily	FALSE	NA
cluster40	XANPAGTX0501_001497-T1	NA	FALSE	NA
cluster40	XANPAGTX0501_001498-T1	IPR012340 Nucleic acid-binding, OB-fold	FALSE	NA
cluster40	XANPAGTX0501_001496-T1	NA	FALSE	NA
cluster41	XANPAGTX0501_001710-T1	IPR007577 Glycosyltransferase, DXD sugar-binding motif, IPR029044 Nucleotide-diphospho-sugar transferases	FALSE	NA
cluster41	XANPAGTX0501_001712-T1	IPR001227 Acyl transferase domain superfamily, IPR006162 Phosphopantetheine attachment site, IPR009081 Phosphopantetheine binding ACP domain, IPR011032 GroES-like superfamily, IPR013154 Alcohol dehydrogenase-like, N-terminal, IPR013216 Methyltransferase type 11, IPR013217 Methyltransferase type 12, IPR013968 Polyketide synthase, ketoreductase domain, IPR014030 Beta-ketoacyl synthase, N-terminal, IPR014031 Beta-ketoacyl synthase, C-terminal, IPR014043 Acyl transferase, IPR016035 Acyl transferase/acyl hydrolase/lysophospholipase, IPR016036 Malonyl-CoA ACP transacylase, ACP-binding, IPR016039 Thiolase-like, IPR018201 Beta-ketoacyl synthase, active site, IPR020801 None, IPR020806 Polyketide synthase, phosphopantetheine-binding domain, IPR020807 Polyketide synthase, dehydratase domain, IPR020841 Polyketide synthase, beta-ketoacyl synthase domain, IPR020843 Polyketide synthase, enoylreductase domain, IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily, IPR032821 Polyketide synthase, C-terminal extension, IPR036291 NAD(P)-binding domain superfamily, IPR036736 ACP-like superfamily, IPR042104 Polyketide synthase, dehydratase domain superfamily	FALSE	NA
cluster41	XANPAGTX0501_010750-T1	NA	FALSE	NA
cluster41	XANPAGTX0501_001713-T1	IPR000073 Alpha/beta hydrolase fold-1, IPR005152 Lipase, secreted, IPR022742 Serine aminopeptidase, S33, IPR029058 Alpha/Beta hydrolase fold	FALSE	NA
cluster41	XANPAGTX0501_001708-T1	NA	TRUE	NA
cluster42	XANPAGTX0501_009317-T1	IPR008979 Galactose-binding-like domain superfamily	TRUE	NA
cluster42	XANPAGTX0501_009340-T1	NA	TRUE	NA
cluster42	XANPAGTX0501_009318-T1	IPR011333 SKP1/BTB/POZ domain superfamily	FALSE	NA
cluster42	XANPAGTX0501_009342-T1	NA	FALSE	NA
cluster42	XANPAGTX0501_009341-T1	NA	FALSE	NA
cluster42	XANPAGTX0501_009322-T1	NA	FALSE	NA
cluster42	XANPAGTX0501_009326-T1	NA	FALSE	NA
cluster42	XANPAGTX0501_009321-T1	NA	FALSE	NA
cluster42	XANPAGTX0501_009316-T1	IPR001810 F-box domain, IPR036047 F-box-like domain superfamily	FALSE	NA
cluster42	XANPAGTX0501_009311-T1	IPR008427 Extracellular membrane protein, CFEM domain	TRUE	NA
cluster42	XANPAGTX0501_009320-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE	NA
cluster42	XANPAGTX0501_009310-T1	IPR032805 Wax synthase domain	FALSE	NA
cluster42	XANPAGTX0501_009331-T1	NA	FALSE	NA
cluster42	XANPAGTX0501_009332-T1	NA	FALSE	NA
cluster43	XANPAGTX0501_009435-T1	NA	FALSE	NA
cluster43	XANPAGTX0501_009437-T1	NA	FALSE	NA
cluster43	XANPAGTX0501_009438-T1	NA	FALSE	NA
cluster43	XANPAGTX0501_009439-T1	NA	FALSE	NA
cluster43	XANPAGTX0501_009436-T1	IPR000330 SNF2, N-terminal, IPR001650 Helicase, C-terminal, IPR001841 Zinc finger, RING-type, IPR013083 Zinc finger, RING/FYVE/PHD-type, IPR014001 Helicase superfamily 1/2, ATP-binding domain, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR038718 SNF2-like, N-terminal domain superfamily	FALSE	NA
cluster44	XANPAGTX0501_009558-T1	IPR000719 Protein kinase domain, IPR011009 Protein kinase-like domain superfamily, IPR036465 von Willebrand factor A-like domain superfamily	FALSE	NA
cluster44	XANPAGTX0501_009557-T1	IPR003615 HNH nuclease	FALSE	NA
cluster44	XANPAGTX0501_009566-T1	NA	FALSE	NA
cluster44	XANPAGTX0501_009555-T1	NA	FALSE	NA
cluster44	XANPAGTX0501_009559-T1	NA	FALSE	NA
cluster45	XANPAGTX0501_009670-T1	IPR000845 Nucleoside phosphorylase domain, IPR002110 Ankyrin repeat, IPR007111 NACHT nucleoside triphosphatase, IPR020683 Domain of unknown function DUF3447, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR035994 Nucleoside phosphorylase superfamily, IPR036770 Ankyrin repeat-containing domain superfamily	FALSE	NA
cluster45	XANPAGTX0501_009672-T1	NA	FALSE	NA
cluster45	XANPAGTX0501_009671-T1	NA	FALSE	NA
cluster45	XANPAGTX0501_009668-T1	NA	TRUE	NA
cluster45	XANPAGTX0501_009673-T1	IPR003593 AAA+ ATPase domain, IPR003959 ATPase, AAA-type, core, IPR027417 P-loop containing nucleoside triphosphate hydrolase	FALSE	NA
cluster45	XANPAGTX0501_009669-T1	IPR003689 Zinc/iron permease	FALSE	NA
cluster45	XANPAGTX0501_009666-T1	NA	FALSE	NA
cluster46	XANPAGTX0501_009688-T1	IPR000254 Cellulose-binding domain, fungal, IPR035971 Cellulose-binding domain superfamily, IPR036908 RlpA-like domain superfamily	TRUE	NA
cluster46	XANPAGTX0501_009689-T1	NA	TRUE	NA
cluster46	XANPAGTX0501_009690-T1	NA	TRUE	NA
cluster47	XANPAGTX0501_009730-T1	NA	TRUE	Cluster_1
cluster47	XANPAGTX0501_009731-T1	IPR005197 Glycoside hydrolase family 71	TRUE	Cluster_1
cluster47	XANPAGTX0501_009734-T1	NA	FALSE	Cluster_1
cluster47	XANPAGTX0501_009738-T1	IPR001810 F-box domain, IPR032675 Leucine-rich repeat domain superfamily, IPR036047 F-box-like domain superfamily	FALSE	NA
cluster48	XANPAGTX0501_009872-T1	NA	FALSE	Cluster_1
cluster48	XANPAGTX0501_009876-T1	IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily	FALSE	NA
cluster48	XANPAGTX0501_009883-T1	NA	FALSE	NA
cluster48	XANPAGTX0501_009887-T1	NA	TRUE	NA
cluster48	XANPAGTX0501_009875-T1	NA	FALSE	NA
cluster48	XANPAGTX0501_009886-T1	NA	TRUE	NA
cluster48	XANPAGTX0501_009881-T2	IPR004212 GTF2I-like repeat	FALSE	NA
cluster48	XANPAGTX0501_009873-T1	NA	FALSE	Cluster_1
cluster49	XANPAGTX0501_010016-T2	IPR000172 Glucose-methanol-choline oxidoreductase, N-terminal, IPR007867 Glucose-methanol-choline oxidoreductase, C-terminal, IPR012132 Glucose-methanol-choline oxidoreductase, IPR036188 FAD/NAD(P)-binding domain superfamily	FALSE	NA
cluster49	XANPAGTX0501_010022-T1	NA	TRUE	NA
cluster49	XANPAGTX0501_010026-T1	IPR018392 LysM domain, IPR036779 LysM domain superfamily	TRUE	NA
cluster49	XANPAGTX0501_010021-T1	NA	TRUE	NA
cluster49	XANPAGTX0501_010016-T1	IPR000172 Glucose-methanol-choline oxidoreductase, N-terminal, IPR007867 Glucose-methanol-choline oxidoreductase, C-terminal, IPR012132 Glucose-methanol-choline oxidoreductase, IPR036188 FAD/NAD(P)-binding domain superfamily	FALSE	NA
cluster49	XANPAGTX0501_010023-T1	NA	FALSE	NA
cluster49	XANPAGTX0501_010027-T1	NA	TRUE	NA
cluster50	XANPAGTX0501_010035-T1	IPR002922 Thiazole biosynthetic enzyme Thi4 family, IPR027495 Thiamine thiazole synthase, IPR036188 FAD/NAD(P)-binding domain superfamily	FALSE	NA
cluster50	XANPAGTX0501_010040-T1	NA	TRUE	NA
cluster50	XANPAGTX0501_010044-T1	IPR002937 Amine oxidase, IPR036188 FAD/NAD(P)-binding domain superfamily	TRUE	NA
cluster50	XANPAGTX0501_010038-T3	IPR000581 Dihydroxy-acid/6-phosphogluconate dehydratase, IPR004404 Dihydroxy-acid dehydratase, IPR020558 Dihydroxy-acid/6-phosphogluconate dehydratase, conserved site, IPR037237 IlvD/EDD, N-terminal domain, IPR042096 Dihydroxy-acid dehydratase, C-terminal	FALSE	NA
cluster50	XANPAGTX0501_010045-T1	IPR002937 Amine oxidase, IPR036188 FAD/NAD(P)-binding domain superfamily	FALSE	NA
cluster50	XANPAGTX0501_010039-T1	NA	FALSE	NA
cluster51	XANPAGTX0501_001936-T1	NA	FALSE	NA
cluster51	XANPAGTX0501_001926-T1	NA	FALSE	NA
cluster51	XANPAGTX0501_001921-T1	IPR025714 Methyltransferase domain, IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily, IPR041698 Methyltransferase domain 25	FALSE	NA
cluster51	XANPAGTX0501_001930-T1	NA	FALSE	NA
cluster51	XANPAGTX0501_001937-T1	NA	FALSE	NA
cluster51	XANPAGTX0501_001927-T1	NA	FALSE	NA
cluster51	XANPAGTX0501_001935-T1	NA	TRUE	NA
cluster52	XANPAGTX0501_001959-T1	IPR000095 CRIB domain, IPR000719 Protein kinase domain, IPR008271 Serine/threonine-protein kinase, active site, IPR011009 Protein kinase-like domain superfamily, IPR017441 Protein kinase, ATP binding site, IPR033923 p21 activated kinase binding domain, IPR036936 CRIB domain superfamily	FALSE	NA
cluster52	XANPAGTX0501_001967-T1	NA	FALSE	Cluster_1
cluster52	XANPAGTX0501_001954-T1	NA	FALSE	NA
cluster52	XANPAGTX0501_001965-T1	NA	FALSE	Cluster_1
cluster52	XANPAGTX0501_001970-T1	NA	TRUE	Cluster_1
cluster52	XANPAGTX0501_001963-T1	NA	FALSE	Cluster_1
cluster52	XANPAGTX0501_001956-T1	NA	FALSE	NA
cluster52	XANPAGTX0501_001962-T1	NA	FALSE	Cluster_1
cluster52	XANPAGTX0501_001953-T1	NA	FALSE	NA
cluster52	XANPAGTX0501_001961-T1	NA	FALSE	Cluster_1
cluster52	XANPAGTX0501_001966-T1	NA	FALSE	Cluster_1
cluster52	XANPAGTX0501_001964-T1	IPR001611 Leucine-rich repeat, IPR003591 Leucine-rich repeat, typical subtype, IPR019487 RAM signalling pathway, SOG2, IPR032675 Leucine-rich repeat domain superfamily	FALSE	Cluster_1
cluster52	XANPAGTX0501_001955-T1	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR001451 Hexapeptide repeat, IPR002110 Ankyrin repeat, IPR011004 Trimeric LpxA-like superfamily, IPR018357 Hexapeptide transferase, conserved site, IPR020683 Domain of unknown function DUF3447, IPR024688 Maltose/galactoside acetyltransferase, IPR036770 Ankyrin repeat-containing domain superfamily, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	FALSE	NA
cluster52	XANPAGTX0501_001958-T1	IPR001356 Homeobox domain, IPR009057 Homeobox-like domain superfamily, IPR017970 Homeobox, conserved site	FALSE	NA
cluster52	XANPAGTX0501_001960-T1	NA	FALSE	Cluster_1
cluster52	XANPAGTX0501_001957-T1	NA	FALSE	NA
cluster53	XANPAGTX0501_002182-T1	NA	FALSE	Cluster_3
cluster53	XANPAGTX0501_002186-T1	NA	TRUE	Cluster_3
cluster53	XANPAGTX0501_002184-T1	NA	FALSE	Cluster_3
cluster53	XANPAGTX0501_002190-T1	IPR001425 Archaeal/bacterial/fungal rhodopsins, IPR018229 Rhodopsin, retinal binding site	FALSE	Cluster_3
cluster53	XANPAGTX0501_002191-T1	NA	TRUE	Cluster_3
cluster53	XANPAGTX0501_002185-T1	NA	FALSE	Cluster_3
cluster53	XANPAGTX0501_002183-T1	NA	FALSE	Cluster_3
cluster54	XANPAGTX0501_002355-T1	NA	FALSE	NA
cluster54	XANPAGTX0501_002358-T1	NA	FALSE	NA
cluster54	XANPAGTX0501_002357-T1	NA	FALSE	NA
cluster54	XANPAGTX0501_002359-T1	NA	FALSE	NA
cluster54	XANPAGTX0501_002356-T1	IPR006140 D-isomer specific 2-hydroxyacid dehydrogenase, NAD-binding domain, IPR029752 D-isomer specific 2-hydroxyacid dehydrogenase, NAD-binding domain conserved site 1, IPR029753 D-isomer specific 2-hydroxyacid dehydrogenase, NAD-binding domain conserved site, IPR036291 NAD(P)-binding domain superfamily	FALSE	NA
cluster55	XANPAGTX0501_002410-T1	NA	FALSE	NA
cluster55	XANPAGTX0501_002409-T1	IPR001338 Hydrophobin	TRUE	NA
cluster55	XANPAGTX0501_002412-T2	NA	TRUE	NA
cluster55	XANPAGTX0501_002411-T1	NA	FALSE	NA
cluster55	XANPAGTX0501_002412-T1	NA	TRUE	NA
cluster55	XANPAGTX0501_002408-T1	NA	FALSE	NA
cluster56	XANPAGTX0501_002441-T1	NA	FALSE	NA
cluster56	XANPAGTX0501_002437-T1	IPR001077 O-methyltransferase domain, IPR016461 O-methyltransferase COMT-type, IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily, IPR036388 Winged helix-like DNA-binding domain superfamily, IPR036390 Winged helix DNA-binding domain superfamily	FALSE	NA
cluster56	XANPAGTX0501_002427-T1	IPR001138 Zn(2)Cys(6) fungal-type DNA-binding domain, IPR036864 Zn(2)-C6 fungal-type DNA-binding domain superfamily	FALSE	NA
cluster56	XANPAGTX0501_002433-T1	NA	FALSE	NA
cluster56	XANPAGTX0501_002440-T1	NA	FALSE	NA
cluster56	XANPAGTX0501_002435-T1	IPR002110 Ankyrin repeat, IPR020683 Domain of unknown function DUF3447, IPR036770 Ankyrin repeat-containing domain superfamily	FALSE	NA
cluster56	XANPAGTX0501_002428-T1	NA	FALSE	NA
cluster56	XANPAGTX0501_002434-T1	IPR002110 Ankyrin repeat, IPR020683 Domain of unknown function DUF3447, IPR036770 Ankyrin repeat-containing domain superfamily	FALSE	NA
cluster56	XANPAGTX0501_002429-T1	IPR001077 O-methyltransferase domain, IPR016461 O-methyltransferase COMT-type, IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily, IPR036388 Winged helix-like DNA-binding domain superfamily, IPR036390 Winged helix DNA-binding domain superfamily	FALSE	NA
cluster56	XANPAGTX0501_002436-T1	IPR002110 Ankyrin repeat, IPR003593 AAA+ ATPase domain, IPR007111 NACHT nucleoside triphosphatase, IPR020683 Domain of unknown function DUF3447, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR031348 Fungal N-terminal domain of STAND protein, IPR036770 Ankyrin repeat-containing domain superfamily	FALSE	NA
cluster56	XANPAGTX0501_002439-T1	NA	FALSE	NA
cluster56	XANPAGTX0501_002424-T1	NA	FALSE	NA
cluster57	XANPAGTX0501_010180-T1	NA	FALSE	NA
cluster57	XANPAGTX0501_010175-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE	NA
cluster57	XANPAGTX0501_010169-T1	IPR035992 Ricin B-like lectins	FALSE	NA
cluster57	XANPAGTX0501_010173-T1	NA	FALSE	NA
cluster57	XANPAGTX0501_010171-T1	NA	FALSE	NA
cluster57	XANPAGTX0501_010172-T1	IPR010730 Heterokaryon incompatibility	FALSE	NA
cluster57	XANPAGTX0501_010174-T1	NA	FALSE	NA
cluster57	XANPAGTX0501_010170-T1	IPR000772 Ricin B, lectin domain, IPR035992 Ricin B-like lectins	TRUE	NA
cluster58	XANPAGTX0501_010244-T1	IPR000182 GNAT domain, IPR016181 Acyl-CoA N-acyltransferase	FALSE	NA
cluster58	XANPAGTX0501_010248-T1	IPR000073 Alpha/beta hydrolase fold-1, IPR029058 Alpha/Beta hydrolase fold	FALSE	NA
cluster58	XANPAGTX0501_010247-T1	NA	TRUE	NA
cluster58	XANPAGTX0501_010250-T1	NA	TRUE	NA
cluster59	XANPAGTX0501_010478-T1	IPR000589 Ribosomal protein S15, IPR009068 S15/NS1, RNA-binding	FALSE	NA
cluster59	XANPAGTX0501_010475-T1	IPR007111 NACHT nucleoside triphosphatase, IPR027417 P-loop containing nucleoside triphosphate hydrolase	FALSE	NA
cluster59	XANPAGTX0501_010476-T1	NA	FALSE	NA
cluster59	XANPAGTX0501_010479-T1	NA	FALSE	NA
cluster60	XANPAGTX0501_010557-T1	IPR000073 Alpha/beta hydrolase fold-1, IPR022742 Serine aminopeptidase, S33, IPR029058 Alpha/Beta hydrolase fold	FALSE	NA
cluster60	XANPAGTX0501_010558-T1	IPR000719 Protein kinase domain, IPR008266 Tyrosine-protein kinase, active site, IPR011009 Protein kinase-like domain superfamily, IPR017441 Protein kinase, ATP binding site	FALSE	NA
cluster60	XANPAGTX0501_010559-T1	NA	FALSE	NA
cluster60	XANPAGTX0501_010556-T1	IPR000719 Protein kinase domain, IPR008271 Serine/threonine-protein kinase, active site, IPR011009 Protein kinase-like domain superfamily	FALSE	NA
cluster60	XANPAGTX0501_010551-T1	IPR006094 FAD linked oxidase, N-terminal, IPR016166 FAD-binding domain, PCMH-type, IPR016169 FAD-binding, type PCMH, subdomain 2, IPR036318 FAD-binding, type PCMH-like superfamily	FALSE	NA
cluster60	XANPAGTX0501_010552-T1	NA	FALSE	NA
cluster61	XANPAGTX0501_010572-T1	NA	FALSE	NA
cluster61	XANPAGTX0501_010571-T1	IPR029498 Prion-inhibition and propagation, HeLo domain, IPR038305 HeLo domain superfamily	FALSE	NA
cluster61	XANPAGTX0501_010570-T1	IPR002182 NB-ARC, IPR010730 Heterokaryon incompatibility, IPR011990 Tetratricopeptide-like helical domain superfamily, IPR013026 None, IPR019734 Tetratricopeptide repeat, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR031352 NACHT-NTPase and P-loop NTPases, N-terminal domain, IPR041664 Orc1-like, AAA ATPase domain	FALSE	NA
cluster62	XANPAGTX0501_002486-T1	IPR011701 Major facilitator superfamily, IPR020846 Major facilitator superfamily domain, IPR036259 MFS transporter superfamily	FALSE	Cluster_2
cluster62	XANPAGTX0501_002483-T3	IPR007229 Nicotinate phosphoribosyltransferase family, IPR036068 Nicotinate phosphoribosyltransferase-like, C-terminal, IPR040727 Nicotinate phosphoribosyltransferase, N-terminal domain, IPR041525 Nicotinate/nicotinamide phosphoribosyltransferase	FALSE	Cluster_2
cluster62	XANPAGTX0501_002491-T1	IPR021848 Haem-dependent oxidative N-demethylase, alpha subunit-like	FALSE	Cluster_2
cluster62	XANPAGTX0501_002488-T1	IPR000873 AMP-dependent synthetase/ligase domain, IPR009081 Phosphopantetheine binding ACP domain, IPR010071 Amino acid adenylation domain, IPR010080 Thioester reductase-like domain, IPR013120 Fatty acyl-coenzyme A reductase, NAD-binding domain, IPR020845 AMP-binding, conserved site, IPR036291 NAD(P)-binding domain superfamily, IPR036736 ACP-like superfamily, IPR042099 ANL, N-terminal domain	FALSE	Cluster_2
cluster62	XANPAGTX0501_002487-T1	IPR001585 Transaldolase/Fructose-6-phosphate aldolase, IPR013785 Aldolase-type TIM barrel, IPR018225 Transaldolase, active site	FALSE	Cluster_2
cluster62	XANPAGTX0501_002490-T1	IPR036291 NAD(P)-binding domain superfamily	FALSE	Cluster_2
cluster63	XANPAGTX0501_002503-T1	NA	FALSE	NA
cluster63	XANPAGTX0501_002505-T1	NA	FALSE	NA
cluster63	XANPAGTX0501_002504-T1	IPR008441 AfumC-like glycosyltransferase, IPR029044 Nucleotide-diphospho-sugar transferases	FALSE	NA
cluster63	XANPAGTX0501_002506-T1	NA	FALSE	NA
cluster63	XANPAGTX0501_002514-T1	NA	TRUE	NA
cluster64	XANPAGTX0501_002562-T1	IPR004045 Glutathione S-transferase, N-terminal, IPR004046 Glutathione S-transferase, C-terminal, IPR010987 Glutathione S-transferase, C-terminal-like, IPR036249 Thioredoxin-like superfamily, IPR036282 Glutathione S-transferase, C-terminal domain superfamily, IPR040079 Glutathione transferase family	FALSE	NA
cluster64	XANPAGTX0501_002566-T1	IPR002893 Zinc finger, MYND-type, IPR027974 Domain of unknown function DUF4470	FALSE	NA
cluster64	XANPAGTX0501_002565-T1	NA	TRUE	NA
cluster65	XANPAGTX0501_002780-T1	IPR000210 BTB/POZ domain, IPR011333 SKP1/BTB/POZ domain superfamily	FALSE	NA
cluster65	XANPAGTX0501_002783-T1	NA	FALSE	NA
cluster65	XANPAGTX0501_002791-T1	IPR024079 Metallopeptidase, catalytic domain superfamily	FALSE	NA
cluster65	XANPAGTX0501_002792-T1	NA	FALSE	NA
cluster66	XANPAGTX0501_002946-T1	NA	FALSE	NA
cluster66	XANPAGTX0501_002943-T1	NA	FALSE	NA
cluster66	XANPAGTX0501_002947-T1	IPR000330 SNF2, N-terminal, IPR001650 Helicase, C-terminal, IPR001841 Zinc finger, RING-type, IPR013083 Zinc finger, RING/FYVE/PHD-type, IPR014001 Helicase superfamily 1/2, ATP-binding domain, IPR017907 Zinc finger, RING-type, conserved site, IPR018957 Zinc finger, C3HC4 RING-type, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR038718 SNF2-like, N-terminal domain superfamily	FALSE	NA
cluster67	XANPAGTX0501_002961-T1	NA	FALSE	NA
cluster67	XANPAGTX0501_002962-T1	NA	FALSE	NA
cluster67	XANPAGTX0501_002967-T1	NA	FALSE	NA
cluster68	XANPAGTX0501_010596-T1	NA	FALSE	NA
cluster68	XANPAGTX0501_010597-T1	NA	FALSE	NA
cluster68	XANPAGTX0501_010598-T1	NA	FALSE	NA
cluster68	XANPAGTX0501_010603-T1	NA	FALSE	NA
cluster68	XANPAGTX0501_010604-T1	IPR002110 Ankyrin repeat, IPR020683 Domain of unknown function DUF3447, IPR036770 Ankyrin repeat-containing domain superfamily	FALSE	NA
cluster68	XANPAGTX0501_010605-T1	IPR002110 Ankyrin repeat, IPR020683 Domain of unknown function DUF3447, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR036770 Ankyrin repeat-containing domain superfamily	FALSE	NA
cluster68	XANPAGTX0501_010606-T1	IPR002110 Ankyrin repeat, IPR020683 Domain of unknown function DUF3447, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR036770 Ankyrin repeat-containing domain superfamily	FALSE	NA
cluster68	XANPAGTX0501_010607-T1	IPR002110 Ankyrin repeat, IPR003593 AAA+ ATPase domain, IPR007111 NACHT nucleoside triphosphatase, IPR020683 Domain of unknown function DUF3447, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR031348 Fungal N-terminal domain of STAND protein, IPR036770 Ankyrin repeat-containing domain superfamily	FALSE	NA
cluster68	XANPAGTX0501_010608-T1	IPR002110 Ankyrin repeat, IPR003593 AAA+ ATPase domain, IPR007111 NACHT nucleoside triphosphatase, IPR020683 Domain of unknown function DUF3447, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR031348 Fungal N-terminal domain of STAND protein, IPR036770 Ankyrin repeat-containing domain superfamily	FALSE	NA
cluster69	XANPAGTX0501_003173-T1	NA	FALSE	Cluster_1
cluster69	XANPAGTX0501_003171-T1	NA	FALSE	Cluster_1
cluster69	XANPAGTX0501_003172-T1	NA	FALSE	Cluster_1
cluster70	XANPAGTX0501_003213-T1	IPR001810 F-box domain, IPR032675 Leucine-rich repeat domain superfamily, IPR036047 F-box-like domain superfamily	FALSE	NA
cluster70	XANPAGTX0501_003198-T1	IPR022085 Oxopyrrolidines biosynthesis cluster protein G	FALSE	Cluster_2
cluster70	XANPAGTX0501_003205-T1	IPR001128 Cytochrome P450, IPR002401 Cytochrome P450, E-class, group I, IPR017972 Cytochrome P450, conserved site, IPR036396 Cytochrome P450 superfamily	FALSE	NA
cluster70	XANPAGTX0501_003212-T1	IPR001810 F-box domain, IPR032675 Leucine-rich repeat domain superfamily, IPR036047 F-box-like domain superfamily	FALSE	NA
cluster70	XANPAGTX0501_003200-T1	NA	FALSE	Cluster_2
cluster70	XANPAGTX0501_003211-T1	NA	FALSE	NA
cluster70	XANPAGTX0501_003199-T1	IPR017946 PLC-like phosphodiesterase, TIM beta/alpha-barrel domain superfamily, IPR039559 Altered inheritance of mitochondria protein 6, PI-PLC-like catalytic domain	FALSE	Cluster_2
cluster71	XANPAGTX0501_003289-T1	NA	FALSE	Cluster_4
cluster71	XANPAGTX0501_003282-T1	NA	FALSE	NA
cluster71	XANPAGTX0501_003283-T1	NA	FALSE	NA
cluster71	XANPAGTX0501_003285-T1	IPR008758 Peptidase S28, IPR029058 Alpha/Beta hydrolase fold, IPR042269 Serine carboxypeptidase S28, SKS domain	TRUE	NA
cluster71	XANPAGTX0501_003287-T1	NA	TRUE	Cluster_4
cluster72	XANPAGTX0501_003714-T1	IPR001077 O-methyltransferase domain, IPR016461 O-methyltransferase COMT-type, IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily, IPR036388 Winged helix-like DNA-binding domain superfamily, IPR036390 Winged helix DNA-binding domain superfamily	FALSE	NA
cluster72	XANPAGTX0501_003715-T1	NA	FALSE	NA
cluster72	XANPAGTX0501_003723-T1	NA	FALSE	NA
cluster73	XANPAGTX0501_003766-T1	NA	TRUE	NA
cluster73	XANPAGTX0501_003775-T2	IPR003100 PAZ domain, IPR003165 Piwi domain, IPR012337 Ribonuclease H-like superfamily, IPR014811 Argonaute, linker 1 domain, IPR032472 Argonaute linker 2 domain, IPR032473 Protein argonaute, Mid domain, IPR032474 Protein argonaute, N-terminal, IPR036085 PAZ domain superfamily, IPR036397 Ribonuclease H superfamily	FALSE	NA
cluster73	XANPAGTX0501_003775-T1	IPR003100 PAZ domain, IPR003165 Piwi domain, IPR012337 Ribonuclease H-like superfamily, IPR014811 Argonaute, linker 1 domain, IPR032472 Argonaute linker 2 domain, IPR032473 Protein argonaute, Mid domain, IPR032474 Protein argonaute, N-terminal, IPR036085 PAZ domain superfamily, IPR036397 Ribonuclease H superfamily	FALSE	NA
cluster73	XANPAGTX0501_003767-T1	NA	FALSE	NA
cluster73	XANPAGTX0501_003765-T1	IPR000420 Yeast PIR protein repeat	TRUE	NA
cluster74	XANPAGTX0501_004003-T1	NA	FALSE	NA
cluster74	XANPAGTX0501_004008-T1	NA	FALSE	NA
cluster74	XANPAGTX0501_004006-T1	IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR041677 DNA2/NAM7 helicase, helicase domain, IPR041679 DNA2/NAM7 helicase-like, C-terminal	FALSE	NA
cluster75	XANPAGTX0501_004414-T1	IPR027417 P-loop containing nucleoside triphosphate hydrolase	FALSE	Cluster_2
cluster75	XANPAGTX0501_004416-T1	IPR000246 Peptidase T2, asparaginase 2, IPR029055 Nucleophile aminohydrolases, N-terminal, IPR037464 Threonine aspartase 1	FALSE	Cluster_2
cluster75	XANPAGTX0501_004407-T1	IPR002925 Dienelactone hydrolase, IPR029058 Alpha/Beta hydrolase fold	FALSE	Cluster_2
cluster75	XANPAGTX0501_004415-T1	NA	FALSE	Cluster_2
cluster76	XANPAGTX0501_004429-T1	NA	FALSE	NA
cluster76	XANPAGTX0501_004431-T1	NA	FALSE	NA
cluster76	XANPAGTX0501_004430-T1	NA	FALSE	NA
cluster76	XANPAGTX0501_004428-T1	IPR004695 Transporter protein SLAC1/Mae1/ Ssu1/TehA, IPR030185 Malic acid transport protein, IPR038665 Voltage-dependent anion channel superfamily	FALSE	NA
cluster77	XANPAGTX0501_004520-T1	NA	FALSE	NA
cluster77	XANPAGTX0501_004519-T1	NA	FALSE	NA
cluster77	XANPAGTX0501_004521-T1	IPR008271 Serine/threonine-protein kinase, active site, IPR011009 Protein kinase-like domain superfamily	FALSE	NA
cluster77	XANPAGTX0501_004530-T1	NA	FALSE	NA
cluster77	XANPAGTX0501_004515-T1	IPR032710 NTF2-like domain superfamily, IPR037401 SnoaL-like domain	TRUE	NA
cluster77	XANPAGTX0501_004525-T1	IPR000719 Protein kinase domain, IPR008271 Serine/threonine-protein kinase, active site, IPR011009 Protein kinase-like domain superfamily	FALSE	NA
cluster78	XANPAGTX0501_004956-T1	NA	TRUE	NA
cluster78	XANPAGTX0501_004961-T1	IPR002110 Ankyrin repeat, IPR020683 Domain of unknown function DUF3447, IPR031348 Fungal N-terminal domain of STAND protein, IPR036770 Ankyrin repeat-containing domain superfamily	FALSE	NA
cluster78	XANPAGTX0501_004963-T1	IPR001915 Peptidase M48	FALSE	NA
cluster78	XANPAGTX0501_004965-T1	NA	FALSE	NA
cluster78	XANPAGTX0501_004966-T1	NA	FALSE	NA
cluster79	XANPAGTX0501_004998-T1	IPR000182 GNAT domain, IPR016181 Acyl-CoA N-acyltransferase	FALSE	NA
cluster79	XANPAGTX0501_004997-T1	NA	FALSE	NA
cluster79	XANPAGTX0501_004983-T1	NA	TRUE	NA
cluster79	XANPAGTX0501_004996-T1	IPR002293 Amino acid/polyamine transporter I	FALSE	NA
cluster79	XANPAGTX0501_004991-T1	NA	FALSE	NA
cluster79	XANPAGTX0501_004992-T1	IPR013087 Zinc finger C2H2-type	FALSE	NA
cluster79	XANPAGTX0501_004990-T1	NA	FALSE	NA
cluster80	XANPAGTX0501_005026-T1	NA	FALSE	NA
cluster80	XANPAGTX0501_005021-T1	NA	FALSE	NA
cluster80	XANPAGTX0501_005022-T1	NA	FALSE	NA
cluster80	XANPAGTX0501_005029-T1	NA	FALSE	NA
cluster80	XANPAGTX0501_005027-T1	IPR003370 Chromate transporter, IPR014047 Chromate transporter, long chain	FALSE	NA
cluster80	XANPAGTX0501_005033-T1	NA	FALSE	NA
cluster80	XANPAGTX0501_005028-T1	NA	FALSE	NA
cluster80	XANPAGTX0501_005025-T1	NA	FALSE	NA
cluster81	XANPAGTX0501_005082-T1	IPR000537 UbiA prenyltransferase family	FALSE	Cluster_3
cluster81	XANPAGTX0501_005081-T1	NA	FALSE	Cluster_3
cluster81	XANPAGTX0501_005084-T1	IPR006094 FAD linked oxidase, N-terminal, IPR012951 Berberine/berberine-like, IPR016166 FAD-binding domain, PCMH-type, IPR036318 FAD-binding, type PCMH-like superfamily	FALSE	Cluster_3
cluster81	XANPAGTX0501_005085-T1	NA	FALSE	Cluster_3
cluster81	XANPAGTX0501_005076-T1	IPR000092 Polyprenyl synthetase, IPR008949 Isoprenoid synthase domain superfamily, IPR033749 Polyprenyl synthetase, conserved site	FALSE	Cluster_3
cluster81	XANPAGTX0501_005074-T1	NA	FALSE	Cluster_3
cluster81	XANPAGTX0501_005083-T1	IPR000073 Alpha/beta hydrolase fold-1, IPR029058 Alpha/Beta hydrolase fold	FALSE	Cluster_3
cluster82	XANPAGTX0501_005252-T1	IPR001227 Acyl transferase domain superfamily, IPR009081 Phosphopantetheine binding ACP domain, IPR013217 Methyltransferase type 12, IPR013968 Polyketide synthase, ketoreductase domain, IPR014030 Beta-ketoacyl synthase, N-terminal, IPR014031 Beta-ketoacyl synthase, C-terminal, IPR014043 Acyl transferase, IPR016035 Acyl transferase/acyl hydrolase/lysophospholipase, IPR016036 Malonyl-CoA ACP transacylase, ACP-binding, IPR016039 Thiolase-like, IPR018201 Beta-ketoacyl synthase, active site, IPR020801 None, IPR020806 Polyketide synthase, phosphopantetheine-binding domain, IPR020807 Polyketide synthase, dehydratase domain, IPR020841 Polyketide synthase, beta-ketoacyl synthase domain, IPR029063 S-adenosyl-L-methionine-dependent methyltransferase superfamily, IPR032821 Polyketide synthase, C-terminal extension, IPR036291 NAD(P)-binding domain superfamily, IPR036736 ACP-like superfamily, IPR042104 Polyketide synthase, dehydratase domain superfamily	FALSE	Cluster_2
cluster82	XANPAGTX0501_005256-T1	IPR006094 FAD linked oxidase, N-terminal, IPR012951 Berberine/berberine-like, IPR016166 FAD-binding domain, PCMH-type, IPR036318 FAD-binding, type PCMH-like superfamily	TRUE	Cluster_2
cluster82	XANPAGTX0501_005254-T1	IPR007527 Zinc finger, SWIM-type	FALSE	Cluster_2
cluster82	XANPAGTX0501_005265-T1	IPR001283 Cysteine-rich secretory protein-related, IPR014044 CAP domain, IPR018244 Allergen V5/Tpx-1-related, conserved site, IPR035940 CAP superfamily	FALSE	Cluster_2
cluster82	XANPAGTX0501_005255-T1	IPR016040 NAD(P)-binding domain, IPR036291 NAD(P)-binding domain superfamily	FALSE	Cluster_2
cluster82	XANPAGTX0501_005253-T1	IPR005123 Oxoglutarate/iron-dependent dioxygenase, IPR027443 Isopenicillin N synthase-like superfamily	FALSE	Cluster_2
cluster83	XANPAGTX0501_005280-T1	NA	FALSE	Cluster_3
cluster83	XANPAGTX0501_005278-T1	NA	FALSE	NA
cluster83	XANPAGTX0501_005281-T1	NA	FALSE	Cluster_3
cluster83	XANPAGTX0501_005284-T1	NA	FALSE	Cluster_3
cluster83	XANPAGTX0501_005271-T1	NA	FALSE	NA
cluster83	XANPAGTX0501_005279-T1	NA	FALSE	Cluster_3
cluster84	XANPAGTX0501_005361-T1	NA	TRUE	Cluster_4
cluster84	XANPAGTX0501_005362-T1	NA	FALSE	Cluster_4
cluster84	XANPAGTX0501_005378-T1	IPR002293 Amino acid/polyamine transporter I	FALSE	Cluster_5
cluster84	XANPAGTX0501_005364-T1	NA	TRUE	NA
cluster84	XANPAGTX0501_005371-T1	NA	FALSE	NA
cluster84	XANPAGTX0501_005367-T1	NA	FALSE	NA
cluster84	XANPAGTX0501_005368-T1	NA	FALSE	NA
cluster84	XANPAGTX0501_005370-T1	NA	FALSE	NA
cluster85	XANPAGTX0501_005534-T1	NA	FALSE	NA
cluster85	XANPAGTX0501_005531-T1	IPR008949 Isoprenoid synthase domain superfamily	FALSE	NA
cluster85	XANPAGTX0501_005529-T1	IPR002110 Ankyrin repeat, IPR020683 Domain of unknown function DUF3447, IPR036770 Ankyrin repeat-containing domain superfamily	FALSE	NA
cluster85	XANPAGTX0501_005532-T1	IPR008949 Isoprenoid synthase domain superfamily	FALSE	NA
cluster85	XANPAGTX0501_005530-T1	IPR008949 Isoprenoid synthase domain superfamily	FALSE	NA
cluster85	XANPAGTX0501_005541-T1	NA	FALSE	NA
cluster85	XANPAGTX0501_005533-T1	NA	TRUE	NA
cluster86	XANPAGTX0501_005615-T1	NA	FALSE	NA
cluster86	XANPAGTX0501_005613-T1	IPR003615 HNH nuclease	FALSE	NA
cluster86	XANPAGTX0501_005602-T1	IPR000073 Alpha/beta hydrolase fold-1, IPR000639 Epoxide hydrolase-like, IPR029058 Alpha/Beta hydrolase fold	FALSE	NA
cluster86	XANPAGTX0501_005610-T1	NA	FALSE	NA
cluster86	XANPAGTX0501_005604-T1	IPR015590 Aldehyde dehydrogenase domain, IPR016161 Aldehyde/histidinol dehydrogenase, IPR016162 Aldehyde dehydrogenase, N-terminal, IPR016163 Aldehyde dehydrogenase, C-terminal, IPR029510 Aldehyde dehydrogenase, glutamic acid active site	FALSE	NA
cluster86	XANPAGTX0501_005612-T1	NA	FALSE	NA
cluster86	XANPAGTX0501_005611-T1	NA	FALSE	NA
cluster86	XANPAGTX0501_005614-T1	NA	FALSE	NA
cluster87	XANPAGTX0501_005697-T2	IPR002110 Ankyrin repeat, IPR003593 AAA+ ATPase domain, IPR007111 NACHT nucleoside triphosphatase, IPR020683 Domain of unknown function DUF3447, IPR027417 P-loop containing nucleoside triphosphate hydrolase, IPR031348 Fungal N-terminal domain of STAND protein, IPR036770 Ankyrin repeat-containing domain superfamily	FALSE	NA
cluster87	XANPAGTX0501_005693-T1	NA	FALSE	NA
cluster87	XANPAGTX0501_005695-T1	NA	FALSE	NA
cluster87	XANPAGTX0501_005694-T1	NA	FALSE	NA
cluster87	XANPAGTX0501_005692-T1	IPR000873 AMP-dependent synthetase/ligase domain, IPR009081 Phosphopantetheine binding ACP domain, IPR010071 Amino acid adenylation domain, IPR010080 Thioester reductase-like domain, IPR013120 Fatty acyl-coenzyme A reductase, NAD-binding domain, IPR020845 AMP-binding, conserved site, IPR036291 NAD(P)-binding domain superfamily, IPR036736 ACP-like superfamily, IPR042099 ANL, N-terminal domain	FALSE	NA
cluster87	XANPAGTX0501_005699-T1	IPR010730 Heterokaryon incompatibility	FALSE	NA
cluster88	XANPAGTX0501_005737-T1	IPR002347 Short-chain dehydrogenase/reductase SDR, IPR036291 NAD(P)-binding domain superfamily	FALSE	Cluster_1
cluster88	XANPAGTX0501_005733-T1	NA	TRUE	Cluster_1
cluster88	XANPAGTX0501_005735-T1	IPR018824 Conidiation-specific protein 6	FALSE	Cluster_1
cluster88	XANPAGTX0501_005732-T1	IPR001128 Cytochrome P450, IPR002401 Cytochrome P450, E-class, group I, IPR017972 Cytochrome P450, conserved site, IPR036396 Cytochrome P450 superfamily	FALSE	Cluster_1
cluster89	XANPAGTX0501_005775-T1	NA	FALSE	NA
cluster89	XANPAGTX0501_005766-T1	NA	FALSE	NA
cluster89	XANPAGTX0501_005770-T1	IPR002347 Short-chain dehydrogenase/reductase SDR, IPR036291 NAD(P)-binding domain superfamily	FALSE	NA
cluster89	XANPAGTX0501_005771-T1	IPR001547 Glycoside hydrolase, family 5, IPR017853 Glycoside hydrolase superfamily	TRUE	NA
cluster90	XANPAGTX0501_006137-T1	NA	FALSE	NA
cluster90	XANPAGTX0501_006141-T1	NA	FALSE	NA
cluster90	XANPAGTX0501_006142-T1	NA	TRUE	NA
cluster90	XANPAGTX0501_006143-T1	NA	FALSE	NA
cluster91	XANPAGTX0501_006205-T1	NA	FALSE	NA
cluster91	XANPAGTX0501_006203-T1	IPR001841 Zinc finger, RING-type, IPR002867 IBR domain, IPR013083 Zinc finger, RING/FYVE/PHD-type, IPR017907 Zinc finger, RING-type, conserved site	FALSE	NA
cluster91	XANPAGTX0501_006215-T1	NA	FALSE	NA
cluster91	XANPAGTX0501_006214-T1	NA	FALSE	NA
cluster91	XANPAGTX0501_006204-T1	NA	FALSE	NA
cluster92	XANPAGTX0501_006245-T1	NA	TRUE	NA
cluster92	XANPAGTX0501_006239-T1	NA	FALSE	NA
cluster92	XANPAGTX0501_006250-T1	NA	FALSE	NA
cluster92	XANPAGTX0501_006243-T1	NA	FALSE	NA
cluster92	XANPAGTX0501_006256-T1	NA	FALSE	NA
cluster92	XANPAGTX0501_006232-T1	IPR002347 Short-chain dehydrogenase/reductase SDR, IPR036291 NAD(P)-binding domain superfamily	FALSE	NA
cluster92	XANPAGTX0501_006255-T1	NA	FALSE	NA
cluster92	XANPAGTX0501_006233-T1	IPR001128 Cytochrome P450, IPR002403 Cytochrome P450, E-class, group IV, IPR036396 Cytochrome P450 superfamily	FALSE	NA
cluster92	XANPAGTX0501_006262-T1	NA	FALSE	NA
cluster92	XANPAGTX0501_006253-T1	IPR014849 EKC/KEOPS complex, subunit Gon7	FALSE	NA
cluster92	XANPAGTX0501_006257-T1	IPR000490 Glycoside hydrolase family 17, IPR017853 Glycoside hydrolase superfamily	TRUE	NA
cluster92	XANPAGTX0501_006238-T1	NA	FALSE	NA
cluster92	XANPAGTX0501_006246-T1	NA	FALSE	NA
cluster92	XANPAGTX0501_006237-T1	IPR002347 Short-chain dehydrogenase/reductase SDR, IPR036291 NAD(P)-binding domain superfamily	FALSE	NA

• In culture-upregulated genes, got 49 clusters. 17 of them have only 3 genes, and 45 <10 genes. Maximum count is 13

croc_c<-read.delim("../analysis_and_temp_files/08_dge_culture_lichen/croc_culture_upregulated.txt",header=F)
croc_c$cluster<-paste0("cluster",1:nrow(croc_c))
croc_c<-croc_c %>% separate_longer_delim(V9, delim = " ") %>% filter(V9!="") %>% 
  select(-c(V7,V8,V2,V3))
colnames(croc_c)<-c("contig","start","end","pval","TranscriptID","cluster")
croc_c %>% group_by(cluster) %>% summarize(n=n()) %>% arrange(desc(n)) %>% head()

## # A tibble: 6 × 2
##   cluster       n
##   <chr>     <int>
## 1 cluster31    13
## 2 cluster22    10
## 3 cluster27    10
## 4 cluster38    10
## 5 cluster39     9
## 6 cluster43     9

Only a small fraction if the clusters overlap with BGCs

croc_l3<-croc_l2 %>% 
   mutate(is_SM = ifelse(is.na(antiSMASH),"not_in_SM_cluster","in_SM_cluster")) %>%
  group_by(cluster,is_SM) %>% summarize(n=n()) %>%
   pivot_wider(values_from = n, values_fill = 0, names_from = is_SM)

## `summarise()` has grouped output by 'cluster'. You can override using the
## `.groups` argument.

croc_c2<-croc_c %>% left_join(funannot2) %>% 
  select(cluster,antiSMASH,TranscriptID, InterPro_new,secreted_consensus) 

## Joining with `by = join_by(TranscriptID)`

croc_c3<-croc_c2 %>% 
   mutate(is_SM = ifelse(is.na(antiSMASH),"not_in_SM_cluster","in_SM_cluster")) %>%
  group_by(cluster,is_SM) %>% summarize(n=n()) %>%
   pivot_wider(values_from = n, values_fill = 0, names_from = is_SM)

## `summarise()` has grouped output by 'cluster'. You can override using the
## `.groups` argument.

• Out of 92 upregulated in lichens, 24 overlap with SM clusters
• Out of 49 upregulated in lichens, 10 overlap with SM clusters

Little overlap with high repeat content regions

• Translate CROC coordinates into bed format, so it is easier to visualize

#First, save CROC tables in a bed format
croc_l<-read.delim2("../analysis_and_temp_files/08_dge_culture_lichen/croc_lichen_upregulated.txt",header=F)
write.table(croc_l[,c(1,4,5)],"../analysis_and_temp_files/08_dge_culture_lichen/GTX0501_lichen_upregulated_croc.bed",col.names = F,row.names = F,quote = F,sep="\t")

croc_c<-read.delim2("../analysis_and_temp_files/08_dge_culture_lichen/croc_culture_upregulated.txt",header=F)
write.table(croc_c[,c(1,4,5)],"../analysis_and_temp_files/08_dge_culture_lichen/GTX0501_culture_upregulated_croc.bed",col.names = F,row.names = F,quote = F,sep="\t")

#intersec CROC file with the bed file
sbatch --mem=10G -c 5 --partition=tsl-short --wrap="source package b0ed0698-358b-4c9b-9d21-603ea8d6e478; bedtools coverage -a ../02_mycobiont_genome/analysis_and_temp_files/06_annotate_lecanoro/GTX0501_xanthoria_nuclear_mag_clean_sort.bed -b analysis_and_temp_files/08_dge_culture_lichen/GTX0501_lichen_upregulated_croc.bed > analysis_and_temp_files/08_dge_culture_lichen/GTX0501_xanthoria_nuclear_mag_clean_sort_lichen_upregulated_croc_bedtools.txt"

sbatch --mem=10G -c 5 --partition=tsl-short --wrap="source package b0ed0698-358b-4c9b-9d21-603ea8d6e478; bedtools coverage -a ../02_mycobiont_genome/analysis_and_temp_files/06_annotate_lecanoro/GTX0501_xanthoria_nuclear_mag_clean_sort.bed -b analysis_and_temp_files/08_dge_culture_lichen/GTX0501_culture_upregulated_croc.bed > analysis_and_temp_files/08_dge_culture_lichen/GTX0501_xanthoria_nuclear_mag_clean_sort_culture_upregulated_croc_bedtools.txt"

• Plot separately

#read in separately
croc_l<-read.delim2("../analysis_and_temp_files/08_dge_culture_lichen/GTX0501_xanthoria_nuclear_mag_clean_sort_lichen_upregulated_croc_bedtools.txt",header=F)[,c(1,2,7)]
colnames(croc_l)<-c("contig","window_start","croc")
croc_l$croc<-as.numeric(croc_l$croc)
croc_l<-croc_l %>% mutate(croc_binary_l=if_else(croc>0,1,0))

croc_c<-read.delim2("../analysis_and_temp_files/08_dge_culture_lichen/GTX0501_xanthoria_nuclear_mag_clean_sort_culture_upregulated_croc_bedtools.txt",header=F)[,c(1,2,7)]
colnames(croc_c)<-c("contig","window_start","croc")
croc_c$croc<-as.numeric(croc_c$croc)
croc_c<-croc_c %>% mutate(croc_binary_c=if_else(croc>0,1,0))

• Plot lichen upregulated

ggplot(croc_l,aes(y=fct_reorder(contig,window_start),x=window_start))+
    geom_tile(aes(height=0.1),fill="black")+
  geom_tile(aes(fill=croc_binary_l,alpha=croc_binary_l))+
  xlab("")+ylab("")+
  scale_alpha_continuous(range=c(0,1))+
  scale_fill_gradient(low="#f0f0f0",high="#F8766D")+
   scale_x_continuous(breaks = c(0,1000000,2000000,3000000,4000000),
                     labels = c("0","1 Mbp","2 Mbp","3 Mbp","4 Mbp"))+
  theme_minimal()+
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank())

* Plot culture upregulated

ggplot(croc_c,aes(y=fct_reorder(contig,window_start),x=window_start))+
  geom_tile(aes(height=0.1),fill="black")+
    geom_tile(aes(fill=croc_binary_c,alpha=croc_binary_c))+
  xlab("")+ylab("")+
  scale_alpha_continuous(range=c(0,1))+
  scale_fill_gradient(low="#f0f0f0",high="#619CFF")+
   scale_x_continuous(breaks = c(0,1000000,2000000,3000000,4000000),
                     labels = c("0","1 Mbp","2 Mbp","3 Mbp","4 Mbp"))+
  theme_minimal()+
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank())

• Plot together with repeat content

library(ggnewscale)
library(patchwork)
rep<-read.delim2("../../02_mycobiont_genome/analysis_and_temp_files/06_annotate_lecanoro/GTX0501_xanthoria_nuclear_mag_clean_sort_repeatcov.txt",header=F)[,c(1,2,7)]
colnames(rep)<-c("contig","window_start","repeat_content")
rep$repeat_content<- rep$repeat_content %>% as.numeric()

df2 <- rep %>% left_join(croc_l %>% select(-croc)) %>% 
  left_join(croc_c %>% select(-croc)) %>%
  pivot_longer(-c(contig, window_start),names_to = "parameter",values_to = "value") 

## Joining with `by = join_by(contig, window_start)`
## Joining with `by = join_by(contig, window_start)`

df2$parameter<-plyr::revalue(df2$parameter, c( "repeat_content"="CRepeat%","croc_binary_l"="BLichen_upregulated",
        "croc_binary_c"="ACulture_upregulated"))
df2$contig<-reorder(df2$contig,df2$contig,FUN=function(x) -length(x))

df2<-df2 %>% mutate(panel=case_when(
  contig %in% c("Xp_GTX0501_1","Xp_GTX0501_2","Xp_GTX0501_3",  "Xp_GTX0501_4", 
"Xp_GTX0501_5",  "Xp_GTX0501_6",  "Xp_GTX0501_7",  "Xp_GTX0501_8", 
"Xp_GTX0501_9",  "Xp_GTX0501_10", "Xp_GTX0501_11", "Xp_GTX0501_12",
"Xp_GTX0501_13", "Xp_GTX0501_14", "Xp_GTX0501_15", "Xp_GTX0501_16",
"Xp_GTX0501_17", "Xp_GTX0501_18", "Xp_GTX0501_19") ~ 1,
contig %in% c("Xp_GTX0501_19", "Xp_GTX0501_20","Xp_GTX0501_21", "Xp_GTX0501_22", "Xp_GTX0501_23", "Xp_GTX0501_24","Xp_GTX0501_25", "Xp_GTX0501_26", "Xp_GTX0501_27", "Xp_GTX0501_28","Xp_GTX0501_29", "Xp_GTX0501_30", "Xp_GTX0501_31", "Xp_GTX0501_32",
"Xp_GTX0501_33", "Xp_GTX0501_34", "Xp_GTX0501_35", "Xp_GTX0501_36", "Xp_GTX0501_37", "Xp_GTX0501_38") ~ 2, T ~3))

gg1<-df2 %>% filter(panel==1) |> 
  ggplot() +
  # apply the gradient to group 1
geom_tile(aes(y=parameter,x=window_start,fill=value), 
    filter(df2, parameter == "CRepeat%",panel==1)) +
 scale_fill_gradientn(colours = c("purple", "orange"),guide = 'none')+
  labs(fill = "Repeat%") +
  # start a new scale
new_scale_fill() +
  geom_tile(aes(y=parameter,x=window_start,height=0.25),fill="black", filter(df2, parameter == "BLichen_upregulated",panel==1))+
    geom_tile(aes(y=parameter,x=window_start,fill=value,alpha=value), filter(df2, parameter == "BLichen_upregulated",panel==1))+
  scale_alpha_continuous(range=c(0,1),guide = 'none')+
  scale_fill_gradientn(colours = c("white","#F8766D"),guide = 'none')+
  # start a new scale
  new_scale_fill() +
  geom_tile(aes(y=parameter,x=window_start,height=0.25),fill="black", filter(df2, parameter == "ACulture_upregulated",panel==1))+
    geom_tile(aes(y=parameter,x=window_start,fill=value,alpha=value), filter(df2, parameter == "ACulture_upregulated",panel==1))+
  scale_alpha_continuous(range=c(0,1),guide = 'none')+
  scale_fill_gradientn(colours = c("white","#619CFF"),guide = 'none')+
  scale_x_continuous(breaks = c(0,1000000,2000000,3000000,4000000),
                     labels = c("0","1 Mbp","2 Mbp","3 Mbp","4 Mbp"),expand = c(0, 0))+
  labs(fill = "Culture-upregulated clusters") +  xlab("")+ylab("Contigs")+
  facet_wrap(~contig,ncol=1)+
  theme_classic()+
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
        strip.background = element_blank(),strip.text.x = element_blank(),
        axis.text.y = element_blank(),legend.position="bottom",
        axis.line.y = element_blank(),axis.ticks.y = element_blank())

## Scale for alpha is already present.
## Adding another scale for alpha, which will replace the existing scale.

gg2<-df2 %>% filter(panel==2) |> 
  ggplot() +
  # apply the gradient to group 1
geom_tile(aes(y=parameter,x=window_start,fill=value), 
    filter(df2, parameter == "CRepeat%",panel==2)) +
 scale_fill_gradientn(colours = c("purple", "orange"),guide = 'none')+
  labs(fill = "Repeat%") +
  # start a new scale
new_scale_fill() +
  geom_tile(aes(y=parameter,x=window_start,height=0.25),fill="black", filter(df2, parameter == "BLichen_upregulated",panel==2))+
    geom_tile(aes(y=parameter,x=window_start,fill=value,alpha=value), filter(df2, parameter == "BLichen_upregulated",panel==2))+
  scale_alpha_continuous(range=c(0,1),guide = 'none')+
  scale_fill_gradientn(colours = c("white","#F8766D"),guide = 'none')+
  # start a new scale
  new_scale_fill() +
  geom_tile(aes(y=parameter,x=window_start,height=0.25),fill="black", filter(df2, parameter == "ACulture_upregulated",panel==2))+
    geom_tile(aes(y=parameter,x=window_start,fill=value,alpha=value), filter(df2, parameter == "ACulture_upregulated",panel==2))+
  scale_alpha_continuous(range=c(0,1),guide = 'none')+
  scale_fill_gradientn(colours = c("white","#619CFF"),guide = 'none')+
  scale_x_continuous(breaks = c(0,1000000,2000000,3000000,4000000),
                     labels = c("0","1 Mbp","2 Mbp","3 Mbp","4 Mbp"),expand = c(0, 0))+
  labs(fill = "Culture-upregulated clusters") +  xlab("")+ylab("Contigs")+
  facet_wrap(~contig,ncol=1)+
  theme_classic()+
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
        strip.background = element_blank(),strip.text.x = element_blank(),
        axis.text.y = element_blank(),legend.position="bottom",
        axis.line.y = element_blank(),axis.ticks.y = element_blank())

## Scale for alpha is already present.
## Adding another scale for alpha, which will replace the existing scale.

gg3<-df2 %>% filter(panel==3) |> 
  ggplot() +
  # apply the gradient to group 1
geom_tile(aes(y=parameter,x=window_start,fill=value), 
    filter(df2, parameter == "CRepeat%",panel==3)) +
 scale_fill_gradientn(colours = c("purple", "orange"),guide = 'none')+
  labs(fill = "Repeat%") +
  # start a new scale
new_scale_fill() +
  geom_tile(aes(y=parameter,x=window_start,height=0.25),fill="black", filter(df2, parameter == "BLichen_upregulated",panel==3))+
    geom_tile(aes(y=parameter,x=window_start,fill=value,alpha=value), filter(df2, parameter == "BLichen_upregulated",panel==3))+
  scale_alpha_continuous(range=c(0,1),guide = 'none')+
  scale_fill_gradientn(colours = c("white","#F8766D"),guide = 'none')+
  # start a new scale
  new_scale_fill() +
  geom_tile(aes(y=parameter,x=window_start,height=0.25),fill="black", filter(df2, parameter == "ACulture_upregulated",panel==3))+
    geom_tile(aes(y=parameter,x=window_start,fill=value,alpha=value), filter(df2, parameter == "ACulture_upregulated",panel==3))+
  scale_alpha_continuous(range=c(0,1),guide = 'none')+
  scale_fill_gradientn(colours = c("white","#619CFF"),guide = 'none')+
  scale_x_continuous(breaks = c(0,1000000,2000000,3000000,4000000),
                     labels = c("0","1 Mbp","2 Mbp","3 Mbp","4 Mbp"),expand = c(0, 0))+
  labs(fill = "Culture-upregulated clusters") +  xlab("")+ylab("Contigs")+
  facet_wrap(~contig,ncol=1)+
  theme_classic()+
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
        strip.background = element_blank(),strip.text.x = element_blank(),
        axis.text.y = element_blank(),legend.position="bottom",
        axis.line.y = element_blank(),axis.ticks.y = element_blank())

## Scale for alpha is already present.
## Adding another scale for alpha, which will replace the existing scale.

#scale graph widths
#max(df$window_start[df$panel==1]) / max(df$window_start[df$panel==3]) [1] 29.44444
#max(df$window_start[df$panel==2]) / max(df$window_start[df$panel==3]) [1] 3.666667
gg1+gg2+gg3 + plot_layout(guides = "collect",widths = c(29.4, 3.7, 1)) & theme(legend.position = 'bottom')

* Save figure

plot<-gg1+theme(axis.text = element_text(size=6),
          axis.title = element_text(size=7),
          legend.text = element_text(size=7),
          legend.title = element_text(size=8))+
  gg2+theme(axis.text = element_text(size=6),
          axis.title = element_text(size=7),
          legend.text = element_text(size=7),
          legend.title = element_text(size=8))+
  gg3 +theme(axis.text = element_text(size=6),
          axis.title = element_text(size=7),
          legend.text = element_text(size=7),
          legend.title = element_text(size=8))+
  plot_layout(guides = "collect",widths = c(29.4, 3.7, 1)) & theme(legend.position = 'bottom')
ggsave('../results/croc_clusters_vs_repeats.pdf',plot, width = 5, height = 5)

• How many clusters overlap with high-repeat content regions? to chose the cut-off, made a histogram

ggplot(rep,aes(x=repeat_content))+geom_histogram()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

• Will go with 0.5 cutoff
• 8 (9%) lichen upregulated clusters overlap with high repeat content regions

library(GenomicRanges)

## Loading required package: stats4

## Loading required package: BiocGenerics

## 
## Attaching package: 'BiocGenerics'

## The following object is masked from 'package:limma':
## 
##     plotMA

## The following objects are masked from 'package:lubridate':
## 
##     intersect, setdiff, union

## The following objects are masked from 'package:dplyr':
## 
##     combine, intersect, setdiff, union

## The following objects are masked from 'package:stats':
## 
##     IQR, mad, sd, var, xtabs

## The following objects are masked from 'package:base':
## 
##     anyDuplicated, append, as.data.frame, basename, cbind, colnames,
##     dirname, do.call, duplicated, eval, evalq, Filter, Find, get, grep,
##     grepl, intersect, is.unsorted, lapply, Map, mapply, match, mget,
##     order, paste, pmax, pmax.int, pmin, pmin.int, Position, rank,
##     rbind, Reduce, rownames, sapply, setdiff, sort, table, tapply,
##     union, unique, unsplit, which.max, which.min

## Loading required package: S4Vectors

## Warning: package 'S4Vectors' was built under R version 4.1.3

## 
## Attaching package: 'S4Vectors'

## The following object is masked from 'package:gplots':
## 
##     space

## The following objects are masked from 'package:lubridate':
## 
##     second, second<-

## The following objects are masked from 'package:dplyr':
## 
##     first, rename

## The following object is masked from 'package:tidyr':
## 
##     expand

## The following objects are masked from 'package:base':
## 
##     expand.grid, I, unname

## Loading required package: IRanges

## 
## Attaching package: 'IRanges'

## The following object is masked from 'package:lubridate':
## 
##     %within%

## The following objects are masked from 'package:dplyr':
## 
##     collapse, desc, slice

## The following object is masked from 'package:purrr':
## 
##     reduce

## Loading required package: GenomeInfoDb

croc_l<-read.delim2("../../03_transcriptomic_analysis/analysis_and_temp_files/08_dge_culture_lichen/croc_lichen_upregulated.txt",header=F)
croc_c<-read.delim2("../../03_transcriptomic_analysis/analysis_and_temp_files/08_dge_culture_lichen/croc_culture_upregulated.txt",header=F)

repeat_range <- GRanges(seqnames=rep$contig,ranges=IRanges(rep$window_start, rep$window_start+9999),repeat_content = rep$repeat_content)

croc_l_range <-  GRanges(seqnames=croc_l$V1,ranges=IRanges(croc_l$V4, croc_l$V5),genes=croc_l$V9)
croc_c_range <-  GRanges(seqnames=croc_c$V1,ranges=IRanges(croc_c$V4, croc_c$V5),genes=croc_c$V9)

repeat_croc_l <- repeat_range[countOverlaps(repeat_range, croc_l_range ) > 0]
repeat_croc_l2 <- repeat_croc_l[repeat_croc_l$repeat_content > 0.5]

croc_l_range[countOverlaps(croc_l_range,repeat_croc_l2) > 0]

## GRanges object with 8 ranges and 1 metadata column:
##            seqnames          ranges strand |                  genes
##               <Rle>       <IRanges>  <Rle> |            <character>
##   [1] Xp_GTX0501_12     19342-42764      * | XANPAGTX0501_007271-..
##   [2] Xp_GTX0501_14   137017-141122      * | XANPAGTX0501_008007-..
##   [3] Xp_GTX0501_18   366441-424180      * | XANPAGTX0501_009046-..
##   [4]  Xp_GTX0501_2   399739-424931      * | XANPAGTX0501_001015-..
##   [5]  Xp_GTX0501_2 2298121-2324687      * | XANPAGTX0501_001710-..
##   [6] Xp_GTX0501_21   183347-198083      * | XANPAGTX0501_009435-..
##   [7] Xp_GTX0501_30     15022-50184      * | XANPAGTX0501_010180-..
##   [8]  Xp_GTX0501_8 1503462-1527344      * | XANPAGTX0501_005697-..
##   -------
##   seqinfo: 33 sequences from an unspecified genome; no seqlengths

• 2 culture-upregulated clusters (4%) overlap with high repeat content regions

library(GenomicRanges)
repeat_croc_c <- repeat_range[countOverlaps(repeat_range, croc_c_range ) > 0]
repeat_croc_c2 <- repeat_croc_l[repeat_croc_c$repeat_content > 0.5]

croc_c_range[countOverlaps(croc_c_range,repeat_croc_c2) > 0]

## GRanges object with 2 ranges and 1 metadata column:
##            seqnames        ranges strand |                  genes
##               <Rle>     <IRanges>  <Rle> |            <character>
##   [1] Xp_GTX0501_13 711348-737772      * | XANPAGTX0501_007924-..
##   [2]  Xp_GTX0501_5  27829-113271      * | XANPAGTX0501_003202-..
##   -------
##   seqinfo: 26 sequences from an unspecified genome; no seqlengths